Security Unlocked

Share

Enterprise Resiliency: Breakfast of Champions

Ep. 15

Prior to the pandemic, workdays used to look a whole lot different. If you had a break, you could take a walk to stretch your legs, shake the hands of your co-workers, or get some 1-on-1 face time with the boss. Ahh... those were the days. That close contact we once had is now something that many of us yearn for as we’ve had to abruptly lift and shift from living in our office to working from our home. But communicating and socializing aren’t the only things that were easier back then. The walls of your office have expanded, and with them, the boundaries of your security protocols. Small in-office tasks like patching a server have now become multi-step processes that require remote management, remote updates, and remote administrative control. With that comes the prioritization of resilience and what it means for enterprises, customers, and security teams alike. That’s where remote enterprise resiliency comes into play.  


Today on the pod, we explore the final chapter of the MDDR. Irfan Mirza, Director of Enterprise Continuity and Resilience at Microsoft, wraps up the observations from the report by giving hosts Nic Fillingham and Natalya Godyla the rundown on enterprise resiliency and discusses how we can ensure the highest levels of security while working from home. Irfan explains the Zero trust model and how Microsoft is working to extend security benefits to your kitchen or home office, or...  that make-shift workspace in your closet.  


In the second segment, Andrew Paverd, Senior Researcher on the Microsoft Security Response Center Team and jack of all trades, stops by… and we’re not convinced he’s fully human. He’s here to tell us about the many hats he wears, from safe systems programming to leveraging AI to help with processes within the MSRC, and shares how he has to think like a hacker to prevent attacks. Spoiler alert: he’s a big follower of Murphy’s Law.   


In This Episode, You Will Learn:  

• How classical security models are being challenged 

• What the Zero Trust Model is and how it works  

• The three critical areas of resilience: extending the enterprise boundary, prioritizing resilient performance, and validating the resilience of our human infrastructure.  

• How hackers approach our systems and technologies 

 

Some Questions We Ask: 

• How has security changed as a product of the pandemic? 

• Do we feel like we have secured the remote workforce? 

• What frameworks exist to put a metric around where an organization is in terms of its resiliency? 

• What is Control Flow Guard (CFG) and Control-Flow Integrity? 

• What’s the next stage for the Rust programming language?  


Resources: 

Microsoft Digital Defense Report: 

https://www.microsoft.com/en-us/security/business/security-intelligence-report 


Irfan’s LinkedIn 

https://www.linkedin.com/in/irfanmirzausa/ 


Andrew’s LinkedIn 

https://www.linkedin.com/in/andrewpaverd/ 


Nic’s LinkedIn    

https://www.linkedin.com/in/nicfill/    


Natalia’s LinkedIn    

https://www.linkedin.com/in/nataliagodyla/    


Microsoft Security Blog:     

https://www.microsoft.com/security/blog/   



Transcript

(Full transcript can be found at https://aka.ms/SecurityUnlockedEp15)


Nic Fillingham:

Hello, and welcome to Security Unlocked, a new podcast from Microsoft, where we unlock insights from the latest in news and research from across Microsoft security, engineering and operations teams. I'm Nic Fillingham.


Natalia Godyla:

And I'm Natalia Godyla. In each episode, we'll discuss the latest stories from Microsoft Security, deep dive into the newest threat intel, research and data science.


Nic Fillingham:

And profile some of the fascinating people working on artificial intelligence in Microsoft Security.


Natalia Godyla:

And now let's unlock the pod. Hi Nic, I have big news.


Nic Fillingham:

Big news. Tell me a big news.


Natalia Godyla:

I got a cat. Last night at 8:00 PM, I got a cat.


Nic Fillingham:

Did it come via Amazon Prime drone?


Natalia Godyla:

No.


Nic Fillingham:

Just, that was a very specific time. Like 8:00 PM last night is not usually the time I would associate people getting cats. Tell me how you got your cat.


Natalia Godyla:

It was a lot more conventional. So I had an appointment at the shelter and found a picture of this cat with really nubby legs and immediately-


Nic Fillingham:

(laughs).


Natalia Godyla:

... fell in love obviously. And they actually responded to us and we went and saw the cat, got the cat. The cat is now ours.


Nic Fillingham:

That's awesome. Is the cat's name nubby.


Natalia Godyla:

It's not, but it is on the list of potential name changes. So right now the cat's name is tipper. We're definitely nervous about why the cat was named tipper.


Nic Fillingham:

(laughs).


Natalia Godyla:

We're hiding all of the glass things for right now.


Nic Fillingham:

How do we get to see the cat? Is there, will there be Instagram? Will there be Twitter photos? This is the most important question.


Natalia Godyla:

Wow. I haven't planned that yet.


Nic Fillingham:

You think about that and I'll, uh, I'll start announcing the first guest on this episode.


Natalia Godyla:

(laughs).


Nic Fillingham:

On today's episode, we speak with Irfan Mirza, who is wrapping up our coverage of the Microsoft Digital Defense Report with a conversation about enterprise resiliency. Now, this is really all of the chapters that are in the MDDR, the nation state actors, the increase in cyber crime sophistication, business email compromise that you've heard us talk about on the podcast, all gets sort of wrapped up in a nice little bow in this conversation where we talk about all right, what does it mean, what does it mean for customers? What does it mean for enterprises? What does it mean for security teams? And so we talk about enterprise resiliency. And we actually recorded this interview in late 2020, but here we are, you know, two months later and those findings are just as relevant, just as important. It's a great conversation. And after that, we speak with-


Natalia Godyla:

Andrew Paverd. So he is a senior researcher on the Microsoft Security Response Center team. And his work is well, well, he does a ton of things. I honestly don't know how he has time to pull all of this off. So he does everything from safe systems programming to leveraging AI, to help with processes within MSRC, the Microsoft Security Response Center. And I just recall one of the quotes that he said from our conversation was hackers don't respect your assumptions, or something to that effect, but it's such a succinct way of describing how hackers approach our systems and technology. So another really great conversation with a, a super intelligent researcher here at Microsoft.


Nic Fillingham:

On with the pod.


Natalia Godyla:

On with the pod. Today, we're joined by Irfan Mirza, Director of Enterprise Continuity and Resilience, and we'll be discussing the Microsoft Digital Defense Report and more specifically enterprise resilience. So thank you for being on the show today, Irfan.


Irfan Mirza:

Thanks so much glad to be here. And hope we have a, a great discussion about this. This is such an important topic now.


Natalia Godyla:

Yes, absolutely. And we have been incrementally working through the Microsoft Digital Defense Report, both Nic and I have read it and have had some fantastic conversations with experts. So really looking forward to hearing about the summation around resilience and how that theme is pulled together throughout the report. So let's start it off by just hearing a little bit more about yourself. So can you tell us about your day-to-day? What is your role at Microsoft?


Irfan Mirza:

Well, I lead the enterprise continuity and resilience team and we kind of provide governance overall at the enterprise. We orchestrate sort of all of the, the risk mitigations. We go and uncover what the gaps are, in our enterprise resilience story, we try to measure the effectiveness of what we're doing. We focus on preparedness, meaning that the company's ready and, you know, our critical processes and services are always on the ready. It's a broad space because it spans a very, very large global enterprise. And it's a very deep space because we have to be experts in so many areas. So it's a fun space by saying that.


Natalia Godyla:

Great. And it's really appropriate today then we're talking about the MDDR and enterprise resilience. So let's start at a high level. So can you talk a little bit about just how security has changed as a product of the pandemic? Why is resilience so important now?


Irfan Mirza:

Yeah, it's a great question. A lot of customers are asking that, our field is asking that question, people within the company are asking. Look, we've been 11 months under this pandemic. Maybe, you know, in some places like China, they've been going through it for a little bit longer than us, you know, a couple of months more. What we're finding after having sort of tried to stay resilient through this pandemic, uh, one obviously is on the human side, everyone's doing as much as we possibly can there. But the other part of it is on the enterprise side. What is it that we're having to think about as we think of security and as we think of enterprise resilience?


Irfan Mirza:

There are a couple of big things that I think I would note, one is that, look, when this pandemic hit us, our workforce lifted and shifted. I mean, by that, I mean that we, we, we got up out of our offices and we all left. I mean, we took our laptops and whatever we could home. And we started working remotely. It was a massive, massive lift and shift of personnel, right? We got dispersed. Everybody went to their own homes and most of us have not been back to the office. And it's not just at Microsoft, even, even a lot of our customers and our partners have not gone back to the office at all, right? So that, that's a prolong snow day, if you want to call it that.


Irfan Mirza:

The other thing that happened is our workload went with us. Wasn't just that, "Hey, you know, I'm taking a few days off, I'm going away or going on vacation and, and I'll be checking email periodically." No, I actually took our work with us and we started doing it remotely. So what that's done is it's created sort of a, a need to go back and look at what we thought was our corporate security boundary or perimeter.


Irfan Mirza:

You know, in the classical model, we used to think of the corporation and its facilities as the, the area that we had to go and secure. But now in this dispersed workforce model, we have to think about my kitchen as part of that corporate perimeter. And all of a sudden we have to ensure that, that my kitchen is as secure as the corporate network or as the facilities or the office that I was working from. That paradigm is completely different than anything we'd thought about before.


Nic Fillingham:

And so Irfan, in the MDDR, uh, this section, um, and if you've got the report open, you're playing along at home, I believe it's page 71. This enterprise resiliency is sort of a wrap-up of, of a lot of the observations that are in the MDDR report. It's not a new section. It's as you're getting towards the end of the report, you're looking for, okay, now what does this mean to me? I'm a CSO. I need to make new security policies, security decisions for my organization. This concept of enterprise resiliency is sort of a wrap up of everything that we've seen across cyber crime, across the nation state, et cetera, et cetera. Is that, is that accurate? Is that a good way to sort of read that section in the report?


Irfan Mirza:

Yeah. It is really the, the way to think of it, right.? It's sort of like a, the conclusion, so what, or why is this relevant to me and what can I do about it? When you think about the report and the way that it's structured, look, we, you know, the report goes into great detail about cyber crime as you called out Nic. And then it talks about nation state threats.


Irfan Mirza:

These are newer things to us. We've certainly seen them on the rise, actors that are well-trained, they're well-funded they play a long game, not necessarily a short game, they're looking, they're watching and they're waiting, they're waiting for us to make mistakes or to have gaps, they look for changes in tactics, either ours, uh, they themselves are quite agile, right?


Irfan Mirza:

So when you think about the environment in which we have to think about resilience, and we have to think about security, that environment itself has got new vectors or new threats that are, that are impacting it, right? In addition to that, our workforce has now dispersed, right? We're all over the, all over the globe. We see emerging threats that are, that are, non-classical like ransomware. We see attacks on supply chain. We continue to see malware and malware growing, right?


Irfan Mirza:

And, and so when you think about that, you have to think if I need to secure now my, my dispersed corporate assets and resources, my people, the workload, the data, the services and the processes that are all there, what are the, the sort of three big things I would need to think about? And so this report sort of encapsulates all, all of that. It gives the details of what, what's happening. And, and then page 71 is you say that resilience piece sort of comes back and says, "Look, your security boundaries extended. Like it or not, it is extended at this point. You've got to think beyond that on-site perimeter that we were thinking about before."


Irfan Mirza:

So we have to start thinking differently. And th- there's three critical areas that are sort of called out, acknowledging the security boundary has increased, thinking about resilience and performance, and then validating the resilience of our human infrastructure. This is like new ideas, but these are all becoming imperatives for us. We're having to do this now, whether we like it or not.


Irfan Mirza:

And so this report sort of gives our customers, and, and it's a reflection of what we're doing in the company. It's an open and honest conversation about how we propose to tackle these challenges that we're facing.


Nic Fillingham:

And so Irfan if we can move on to that critical area, number two, that prioritizing resilient performance. When I say the word performance and resilient performance, is that scoped down just to sort of IT infrastructure, or does that go all the way through to the humans, the actual people in the organization and, um, how they are performing their own tasks, their own jobs and the tasks that are part of their, their job and et cetera, et cetera? What's the, I guess what's the scope of that area too?


Irfan Mirza:

As we were thinking about resilience, as you know, shortly after we dispersed the workforce, we started thinking about, about what should be included in our classical understanding of resilience. But when you think about, about typical IT services and online services, and so on, a lot of that work is already being done with the life site reviews that we do and people are paying very close attention to service performance. We have SLAs, we have obligations, we have commitments that we've made that our services will be performing to a certain degree, but there are also business processes that are associated with these services very closely.


Irfan Mirza:

When you think about all of the processes that are involved and services that are involved from the time a customer thinks of buying Office, uh, 365, as an example, to the time that they provision their first mailbox, or they receive their first email, there are dozens of process, business processes.


Irfan Mirza:

Every single service in that chain could be working to 100% efficiency. And yet if the business processes, aren't there, for instance, to process the deal, to process the contract, to process, uh, the customer's payment or, uh, acknowledge receipt of the payment in order to be able to provision the service, all of these processes, all of a sudden have to, we have to make sure that they're also performing.


Irfan Mirza:

So when we start thinking about resilience, up to now, business continuity has focused on, are you ready? Are you prepared? Are your dependencies mapped? Have you, have you done a business impact analysis? Are you validating and testing your preparedness? You know, are you calling down your call tree for instance? But I think where we're going now with true enterprise resilience, especially in this sort of modern


Irfan Mirza:

... day, we're, we're looking at performance, right? What, what is your preparedness resulting in? So if you stop and you think about a child at school, they get homework. Well, the homework really, they bring it home. They do it. They take it back to the teacher. They get graded on it. That's wonderful. This means that the child is ready. But at some point in time, the class or the teacher is going to give them a test, and that test is going to be the measure of performance, right?


Irfan Mirza:

So we need to start thinking of resilience and continuity in the same way. We're prepared. We've done all our homework. Now let's go and see how many outages did you have? How critical were the outages? How long did they last? How many of them were repeat outages? How many of the repeat outages were for services that are supposed to have zero downtown, like services that are always supposed to on like your DNS service or your identity auth- authentication service, right? So, when you start thinking about, uh, resilience from that perspective, now you've got a new set of data that you have to go and capture, or data that you're capturing, you have to now have to have insights from it. You've got to be able to correlate your preparedness, meaning the homework that you've done with your actual performance, your outage and your, and your gap information. All right?


Irfan Mirza:

So that, that's what prioritizing resilient performance is all about. It's about taking realtime enterprise preparedness and mapping it to real time enterprise performance. That tells you if your preparedness is good enough or not, or what it is that you need to do. There's a loop here, a feedback loop that has to be closed. You can't just say that, well, you know, we've done all the exercises theoretically. We're good and we're ready to take on any sort of a crisis or, or, or disaster. Yeah, that's fine. Can we compare it to realtime what you're doing? Can we break glass and see what that looks like? Can we shut you down and or shut down parts of your operation as in the event of an earthquake for instance, or a hurricane wiping out, uh, access to a data center, right? Can we do those things and still be resilient when that happens? So this is what performance and resilience come together in that space.


Natalia Godyla:

So am I right in understanding that beyond, like you said, the theoretical where you think about the policies that you should have in place, and the frameworks that you should have in place, you have the analytics on, you know, the state of, the state of how performant your systems are to date. And then in addition, is there now the need for some sort of stress testing? Like actually figuring out whether an additional load on a system would cause it to break, to not be resilient? Is that now part of the new approach to resilience?


Irfan Mirza:

Yeah. There are, there are several, several things to do here, right? You absolutely said it. There's a stress test. Actually, this pandemic has, is already a stress test in and of itself, right? It's stressing us in a many ways. It's stressing, obviously the psyche and, and, you know, our whole psychology, and our ability to sustain in quarantine, in isolated, in insulated environments and so on. But it's also testing our ability to do the things that we just so, uh, so much took for granted, like the ability to patch a server that's sitting under my desk in the office whenever I needed to, right? That server now has to become a managed item that somebody can manage remotely, patch remotely, update remotely when needed, control administrative access and privileges remotely. But yes, for resilience, I think we need to now collect all of the data that we have been collecting or looking at and saying, can we start to create those correlations between our preparedness and between our real performance?


Irfan Mirza:

But there's another area that this dovetails into which is that of human resilience, right? We talked a little bit earlier about, you know, sort of the whole world enduring this hardship. We need to first and foremost look at our suppliers, subcontractors, people that we're critically dependent on. What is their resilience look like? That's another aspect that we have to go back. In the areas where we have large human resources or, or workforces that are working on our behalf, we need to make sure that they're staying resilient, right?


Irfan Mirza:

We talked on a lot about work/life balance before. Now I think the new buzzword in HR conference rooms is going to be work/life integration. It's completely integrated, and so we need to start thinking about the impact that would have. Are we tracking attrition of our employees, of certain demographics within the employees? Are we looking at disengagement? People just sort of, "Yeah, I'm working from home, but I'm not really being fully engaged." Right? The hallway conversations we used to have are no longer there. And we need to start thinking, are people divesting? Our resources, are they divesting in the workplace? Are they divesting in their, in their work or work/life commitment? These measures are all now having to be sort of like...


Irfan Mirza:

We used to rely on intuition, a look, a hallway gaze, look at the, the snap in somebody's walk as they walked away from you or out of your office. We don't have that anymore. Everybody's relatively stagnant. We're, we're, we're seated. We don't get to see body language that much. We don't get to read that. There's a whole new set of dynamics that are coming into play, and I think smart corporations and smart companies will start looking at this as a very important area to pay attention to.


Nic Fillingham:

How are we measuring that? What tools or sort of techniques, or, or sort of frameworks exist to actually put a metric around this stuff, and determine sort of where, where an organization is in terms of their level of resiliency?


Irfan Mirza:

This question is actually the whole reason why we brought this enterprise resilience sort of a conclusion to this fourth chapter, and, and, you know, the summation of this, of this report.


Irfan Mirza:

What we're doing now is we're saying, look. Things that used to be fundamentally within the domain of IT departments, or used to be fundamentally with, within the domain of live site, or used to be fundamentally in the domain of human resource departments are now all floating up to be corporate imperatives, to be enterprise imperatives. I think the thinking here is that we need to make sure that the data that we've been collecting about, as an example to answer your question, attrition, right? A certain demographic. Millennials, uh, changing jobs, leaving the company, just to pick an example more than anything else. This is no longer just data that the HR Department is interested in, or that recruiting would be interested in, or, or retention would be interested. This is data that's about to significantly impact the enterprise, and it needs to be brought into the enterprise purview.


Irfan Mirza:

Our classical and traditional models of looking at things in silos don't allow us to do that. What we're recommending is that we need to have a broader perspective and try to drive insights from this that do tell a more comprehensive story about our ent- enterprise resilience. That story needs to include the resilience of our services, our business processes, our suppliers, our human capital, our infrastructure, our extended security boundary, our data protection, uh, prevention of data loss, our intrusion detection. I mean, there's such a broad area that we have to cover. That's we're saying. And, and as we implement this new sort of zero trust model, I think the, the effectiveness of that model, how much progress we're making is becoming an enterprise priority, not just something that the IT department is going to go around on it's own.


Nic Fillingham:

Irfan, I wonder if I could put you on the spot, and were there any interesting bits of data that you saw in those first couple months of the shift to remote work where like, yeah, the number of unique devices on the Microsoft corporate network quadrupled in 48 hours. Like any, anything like that? I'd just wondering what, what little stats you may have in hand.


Irfan Mirza:

Yeah. The number of devices and sort of the flavors of devices, we've always anticipated that that's going to be varied. We're cognizant of that. Look, we have, you know, people have PCs. They have MACs. They have Linux machines, and, and they have service o- operating software. There's a lot of different flavors. And, and it's not just the device and the OS that matters, it's also what applications you're running. Some applications we can certify or trust, and others perhaps we can't, or that we still haven't gotten around to, to verifying, right? And all of these sit, and they all perform various functions including intruding and potentially exfiltrating data and Spyware and Malware and all of that. So when you think about that, we've always anticipated it.


Irfan Mirza:

But the one thing that, that we were extremely worried about, and I think a lot of our Enterprise customers were worried about, is the performance of the workforce. What we found very early on in, in the, in the lift and shift phase was that we needed to have a way of measuring is our, our built processes working? Are we checking in the same amount of code as we were before? And we noted a couple of interesting things. We looked at our, our VPN usage and said, what are those numbers look like? Are they going up and down?


Irfan Mirza:

And I think what we found is that initially, the effect was quite comparable to what we had, uh, when we experienced snow days. Schools are shut down. People don't go to work. They're slipping and sliding over here. We're just not prepared for snow weather in, in this state like some of the others. So what happened is, we saw that we were, we were sort of seeing the same level of productivity as snow days. We say that we had the same level of VPN usage as snow days, and we were worried because that, you know, when, when it snows, people usually take the day off, and then they go skiing.


Irfan Mirza:

So what happened? Well, after about a week things started picking back up. People got tired of sort of playing snow day and decided that, you know what? It's time to, to dig in, and human nature, I think, kicked in, the integrity of the workforce kicked in. And sure enough, productivity went up, VPN usage went up, our number of sessions, the duration of sessions. Meetings became shorter.


Nic Fillingham:

Can I tell you hallelujah? (laughs)


Irfan Mirza:

(laughs)


Nic Fillingham:

That's one of the, that's one of the great-


Irfan Mirza:

Absolutely.


Nic Fillingham:

... upsides, isn't it? To this, this new culture of remote work is that we're all meeting for, for less amount of time, which I think, I think is fantastic.


Irfan Mirza:

Look, you know, in times of crisis, whether it's a natural disaster, or a pandemic, or, or a manmade situation such as a war or a civil war, or whatever, I, I think what happens is the amount of resources that you are customarily used to having access to gets limited. The way in which you work shifts. It changes. And so the, the true test of resilience, I think, is when you are able to adapt to those changes gracefully without requiring significant new investment and you're able to still meet and fulfill your customer obligations, your operational expectations. That really is.


Irfan Mirza:

So what you learn in times of hardship are to sort of live, you know, more spartan-like. And that spartan-ism, if there's such a word as that, that's what allows you to stay resilient, to say what are the core things that I need in order to stay up and running? And those fundamental areas become the areas of great investment, the areas that you watch over more carefully, the areas that you measure the performance of, the areas that you look for patterns and, and trends in to try to predict what's happening, right?


Irfan Mirza:

So that is something that carries over from experiences of being in the front lines of a, uh, a war or, or from being, uh, you know, in the midst of a hurricane trying to recover a data center, or an earthquake, or any other, uh, type of power outage, right? These are all the sort of key scenarios that we would be going to look at. And that's one of the things they all have in common. It's really that you don't have the resources or access to the resources that you thought you did, and now you've got to be able to do some things slightly differently.


Natalia Godyla:

Thank you for joining us on the podcast today. It's been great to get your perspective on enterprise resilience. Really fascinating stuff. So, thank you.


Irfan Mirza:

Thank you, Natalia. And, and thank you, Nick. It's been a great conversation. As I look back at this discussion that we had, I feel even, even stronger now that the recommendations that we're making, and the guidance that we're giving our customers and sharing our experiences, becomes really, really important. I think this is something that we're learning as we're going along. We're learning on the journey. We're uncovering things that we didn't know. We're looking at data in a different way. We're, we're trying to figure out how do we sustain ourselves,


Nic Fillingham:

... not just through this pandemic, but also beyond that. And I think the, whatever it is that we're learning, it becomes really important to share. And for our customers and people who are listening to this podcast to share back with us what they've learned, I think that becomes incredibly important because as much as we like to tell people what we're doing, we also want to know what, what people are doing. And so learning that I think will be a great, great experience for us to have as well. So thank you so much for enabling this conversation.


Natalia Godyla:

And now let's meet an expert from the Microsoft security team to learn more about the diverse backgrounds and experiences of the humans creating AI and tech at Microsoft. Welcome back to another episode of Security Unlocked. We are sitting with Andrew Paverd today, senior researcher at Microsoft. Welcome to the show, Andrew.


Andrew Paverd:

Thanks very much. And thanks for having me.


Natalia Godyla:

Oh, we're really excited to chat with you today. So I'm just doing a little research on your background and looks like you've had a really varied experience in terms of security domains consulting for mobile device security. I saw some research on system security. And it looks like now you're focused on confidential computing at Microsoft. So let's start there. Can you talk a little bit about what a day in the life of Andrew looks like at Microsoft?


Andrew Paverd:

Absolutely. I think I have one of the most fascinating roles at Microsoft. On a day-to-day basis, I'm a researcher in the confidential computing group at the Microsoft Research Lab in Cambridge, but I also work very closely with the Microsoft Security Response Center, the MSRC. And so these are the folks who, who are dealing with the frontline incidents and responding to reported vulnerabilities at Microsoft. But I work more on the research side of things. So how do we bridge the gap between research and what's really happening on the, on the front lines? And so I, I think my position is quite unique. It's, it's hard to describe in any other way than that, other than to say, I work on research problems that are relevant to Microsoft security.


Natalia Godyla:

And what are some of those research problems that you're focused on?


Andrew Paverd:

Oh, so it's actually been a really interesting journey since I joined Microsoft two years ago now. My background, as you mentioned, was actually more in systems security. So I had, I previously worked with technologies like trusted execution environments, but since joining Microsoft, I've worked on two really, really interesting projects. The, the first has been around what we call safe systems programming languages.


Andrew Paverd:

So to give a bit more detail about it in the security response center, we've looked at the different vulnerabilities that Microsoft has, has patched and addressed over the years and seen some really interesting statistics that something like 70% of those vulnerabilities for the pa- past decade have been caused by a class of vulnerability called memory corruption. And so the, the question around this is how do we try and solve the root cause of problem? How do we address, uh, memory corruption bugs in a durable way?


Andrew Paverd:

And so people have been looking at both within Microsoft and more broadly at how we could do this by transitioning to a, a different programming paradigm, a more secure programming language, perhaps. So if you think of a lot of software being written in C and C++ this is potentially a, a cause of, of memory corruption bugs. So we were looking at what can we do about changing to safer programming languages for, for systems software. So you might've heard about new languages that have emerged like the Rust programming language. Part of this project was investigating how far we can go with languages like Rust and, and what do we need to do to enable the use of Rust at Microsoft.


Natalia Godyla:

And what was your role with Rust? Is this just the language that you had determined was a safe buyable option, or were you part of potentially producing that language or evolving it to a place that could be safer?


Andrew Paverd:

That's an excellent question. So in, in fact it, it was a bit of both first determining is this a suitable language? Trying to define the evaluation criteria of how we would determine that. But then also once we'd found Rust to be a language that we decided we could potentially run with, there was an element of what do we need to do to bring this up to, let's say to be usable within Microsoft. And actually I, I did quite a bit of work on, on this. We realized that, uh, some Microsoft security technologies that are available in our Microsoft compilers weren't yet available in the Rust compiler. One in particular is, is called control flow guard. It's a Windows security technology and this wasn't available in Rust.


Andrew Paverd:

And so the team I, I work with looked at this and said, okay, we'd like to have this implemented, but nobody was available to implement it at the time. So I said, all right, let me do a prototype implementation and, uh, contributed this to the open source project. And in the end, I ended up following through with that. And so I've, I've been essentially maintaining the, the Microsoft control flow guide implementation for the, the Rust compiler. So really an example of Microsoft contributing to this open source language that, that we hope to be using further.


Nic Fillingham:

Andrew, could you speak a little bit more to control flow guard and control flow integrity? What is that? I know a little bit about it, but I'd love to, for our audience to sort of like expand upon that idea.


Andrew Paverd:

Absolutely. So this is actually an, an example of a technology that goes back to a collaboration between the MSRC, the, the security response center and, and Microsoft Research. This technology control flow guard is really intended to enforce a property that we call control flow integrity. And that simply means that if you think of a program, the control flow of a program jumps through two different functions. And ideally what you want in a well-behaved program is that the control always follows a well-defined paths.


Andrew Paverd:

So for example, you start executing a function at the beginning of the function, rather than halfway through. If for example, you could start executing a function halfway through this leads to all kinds of possible attacks. And so what control flow guard does is it checks whenever your, your program's going to do a bronch, whenever it's going to jump to a different place in the code, it checks that that jump is a valid call target, that you're actually jumping to the correct place. And this is not the attacker trying to compromise your program and launch one of many different types of attacks.


Nic Fillingham:

And so how do you do that? What's the process by which you do en- ensure that control flow?


Andrew Paverd:

Oh, this is really interesting. So this is a technology that's supported by Windows, at the moment it's only available on, on Microsoft Windows. And it works in conjunction between both the compiler and the operating system. So the compiler, when you compile your program gives you a list of the valid code targets. It says, "All right, here are the places in the program where you should be allowed to jump to." And then as the program gets loaded, the, the operating system loads, this list into a highly optimized form so that when the program is running it can do this check really, really quickly to say, is this jump that I'm about to do actually allowed? And so it's this combination of the Windows operating system, plus the compiler instrumentation that, that really make this possible.


Andrew Paverd:

Now this is quite widely used in Windows. Um, we want in fact as much Microsoft software as possible to use this. And so it's really critical that we enable it in any sort of programming language that we want to use.


Nic Fillingham:

How do you protect that list though? So now you, isn't that now a target for potential attackers?


Andrew Paverd:

Absolutely. Yeah. And, and it becomes a bit of a race to, to-


Nic Fillingham:

Cat and mouse.


Andrew Paverd:

... protect different-


Natalia Godyla:

(laughs).


Andrew Paverd:

A bit of, a bit of a cat, cat and mouse game. But at least the nice thing is because list is in one place, we can protect that area of memory to a much greater degree than, than the rest of the program.


Natalia Godyla:

So just taking a step back, can you talk a little bit about your path to security? What roles have you had? What brought you to security? What's informing your role today?


Andrew Paverd:

It's an interesting story of how I ended up working in security. It was when I was applying for PhD programs, I had written a PhD research proposal about a topic I thought was very interesting at the time on mobile cloud computing. And I still think that's a hugely interesting topic. And what happened was I sent this research proposal to an academic at the University of Oxford, where I, I was looking to study, and I didn't hear anything for, for a while.


Andrew Paverd:

And then, a fe- a few days later I got an email back from a completely different academic saying, "This is a very interesting topic. I have a project that's quite similar, but looking at this from a security perspective, would you be interested in doing a PhD in security on, on this topic?" And, so this was my very mind-blowing experience for me. I hadn't considered security in that way before, but I, I took a course on security and found that this was something I was, I was really interested in and ended up accepting the, the PhD offer and did a PhD in system security. And that's really how I got into security. And as they say, the rest is history.


Natalia Godyla:

Is there particular part of security, particular domain within security that is most near and dear to your heart?


Andrew Paverd:

Oh, that's a good question.


Natalia Godyla:

(laughs).


Andrew Paverd:

I think, I, I think for me, security it- itself is such a broad field that we need to ensure that we have security at, at all levels of the stack, at all, places within the chain, in that it's really going to be the weakest link that an attacker will, will go for. And so I've actually changed field perhaps three times so far. This is what keeps it interesting. My PhD work was around trusted computing. And then as I said, I, since joining Microsoft, I've been largely working in both safe systems programming languages and more recently AI and security. And so I think that's what makes security interesting. The, the fact that it's never the same thing two days in a row.


Natalia Godyla:

I think you hit on the secret phrase for this show. So AI and security. Can you talk a little bit about what you've been doing in AI and security within Microsoft?


Andrew Paverd:

Certainly. So about a year ago, as many people in the industry realized that AI is being very widely used and is having great results in so many different products and services, but that there is a risk that AI algorithms and systems themselves may be attacked. For example, I, I know you had some, some guests on your podcast previously, including Ram Shankar Siva Kumar who discussed the Adversarial ML Threat Matrix. And this is primarily the area that I've been working in for the past year. Looking at how AI systems can be, can be attacked from a security or a privacy perspective in collaboration with researchers, from MSR, Cambridge.


Natalia Godyla:

What are you most passionate about? What's next for a couple of these projects? Like with Rust, is there a desire to make that ubiquitously beyond Microsoft? What's the next stage?


Andrew Paverd:

Ab- absolutely.


Natalia Godyla:

Lots of questions. (laughs).


Andrew Paverd:

Yeah. There's a lot of interest in this. So, um, personally, I'm, I'm not working on the SSPL project myself, or I'm, I'm not working on the safe systems programming languages project myself any further, but I know that there's a lot of interest within Microsoft. And so hopefully we'll see some exciting things e- emerging in that space. But I think my focus is really going to be more on the, both the security of AI, and now we're also exploring different areas where we can use AI for security. This is in collaboration, more with the security response center. So looking into different ways that we can automate different processes and use AI for different types of, of analysis. So certainly a lot more to, to come in that space.


Nic Fillingham:

I wanted to come back to Rust for, for a second there, Andrew. So you talked about how the Rust programming language was specifically designed for, correct me on taxonomy, memory integrity. Is that correct?


Andrew Paverd:

For, for memory safety, yeah.


Nic Fillingham:

Memory safety. Got it. What's happening on sort of


Nic Fillingham:

... and sort of the, the flip side of that coin in terms of instead of having to choose a programming language that has memory safety as sort of a core tenet. What's happening with the operating system to ensure that languages that maybe don't have memory safety sort of front and center can be safer to use, and aren't threats or risks to memory integrity are, are sort of mitigated. So what's happening on the operating system side, is that what Control Flow Guard is designed to do? Or are there other things happening to ensure that memory safety is, is not just the responsibility of the programming language?


Andrew Paverd:

Oh, it's, that's an excellent question. So Control Flow Guard certainly helps. It helps to mitigate exploits once there's been an, an initial memory safety violation. But I think that there's a lot of interesting work going on both in the product space, and also in the research space about how do we minimize the amount of software that, that we have to trust. If you accept that software is going to have to bugs, it's going to have vulnerabilities. What we'd like to do, is we'd like to trust as little software as possible.


Andrew Paverd:

And so there's a really interesting effort which is now available in, in Azure under the, the heading of Confidential Computing. Which is this idea that you want to run your security sensitive workloads in a hardware enforced trusted execution environment. So you actually want to take the operating system completely out of what we call the trusted computing base. So that even if there are vulnerabilities in, in the OS, they don't affect your security sensitive workloads. So I think that there's this, this great trend towards confidential computing around compartmentalizing and segmenting the software systems that we're going to be running.


Andrew Paverd:

So removing the operating system from the trusted computing. And, and indeed taking this further, there's already something available in Azure, you can look up Azure Confidential Computing. But there's a lot of research coming in from the, the academic side of things about new technologies and new ways of, of enforcing separation and compartmentalization. And so I think it's part of this full story of, of security that we'll need memory safe programming languages. We'll need compartmentalization techniques, some of which, uh, rely on new hardware features. And we need to put all of this together to really build a, a secure ecosystem.


Nic Fillingham:

I only heard of Confidential Computing recently. I'm sure it's not a new concept. But for me as a sort of a productized thing, I only sort of recently stumbled upon it. I did not realize that there was this gap, there was this delta in terms of data being encrypted at rest, data being encrypted in transit. But then while the data itself was being processed or transformed, that that was a, was a gap. Is that the core idea around Confidential Computing to ensure that at no stage the data is not encrypted? Is, is that sort of what it is?


Andrew Paverd:

Absolutely. And it's one of the key pieces. So we call that isolated execution in the sense that the data is running in a, a trusted environment where only the code within that environment can access that data. So if you think about the hypervisor and the operation system, all of those can be outside of the trusted environment. We don't need to trust those for the correct computation of, of that data. And as soon as that data leaves this trusted environment, for example if it's written out of the CPU into the DRAM, then it gets automatically encrypted.


Andrew Paverd:

And so we have that really, really strong guarantee that only our code is gonna be touching our data. And the second part of this, and this is the really important part, is a, a protocol called remote attestation where this trusted environment can prove to a remote party, for example the, the customer, exactly what code is going to be running over that data. So you have a, a very high degree of assurance of, "This is exactly the code that's gonna be running over my data. And no other code will, will have access to it."


Andrew Paverd:

And the incredibly interesting thing is then, what can we build with these trusted execution environment? What can we build with Confidential Computing? And to bring this back to the, the keyword of your podcast, we're very much looking at confidential machine learning. How do we run machine learning and AI workloads within these trusted execution environments? And, and that unlocks a whole lot of new potential.


Nic Fillingham:

Andrew, do you have any advice for people that are m- maybe still studying or thinking about studying? Uh, I see so you, your initial degree was in, not in computer engineering, was it?


Andrew Paverd:

No. I, I actually did electrical engineering. And then electrical and computer engineering. And by the time I did a PhD, they put me in a computer science department, even though-


Nic Fillingham:

(laughs).


Andrew Paverd:

... I was doing software engineering.


Nic Fillingham:

Yeah. I, so I wonder if folks out there that, that don't have a software or a computer engineering degree, maybe they have a, a different engineering focus or a mathematics focus. Any advice on when and how to consider computer engineering, or sort of the computing field?


Andrew Paverd:

Yeah. Uh, absolutely. Uh, I think, eh, in particular if we're talking about security, I'd say have a look at security. It's often said that people who come with the best security mindsets haven't necessarily gone through the traditional programs. Uh, of course it's fantastic if you can do a, a computer science degree. But if you're coming at this from another area, another, another aspect, you bring a unique perspective to the world of cyber security. And so I would say, have a look at security. See if it's something that, that interests you. You, you might find like I did that it's a completely fascinating topic.


Andrew Paverd:

And the from there, it would just be a question of seeing where your skills and expertise could best fit in to the broad picture of security. We desperately need people working in this field from all different disciplines, bringing a diversity of thought to the field. And so I, I'd highly encourage people to have a look at this.


Natalia Godyla:

And you made a, quite a hard turn into security through the PhD suggestion. It, like you said, it was one course and then you were off. So, uh, what do you think from your background prepared you to make that kind of transition? And maybe there's something there that could inform others along the way.


Andrew Paverd:

I think, yes, it, it's a question of looking at, uh, of understanding the system in as much detail as you possibly can. And then trying to think like, like an attacker. Trying to think about what could go wrong in this system? And as we know, attackers won't respect our assumptions. They will use a system in a different way in which it was designed. And that ability to, to think out of the box, which, which comes from understanding how the system works. And then really just a, a curiosity about security. They call it the security mindset, of perhaps being a little bit cautious and cynical. To say-


Natalia Godyla:

(laughs).


Andrew Paverd:

... "Well, this can go wrong, so it probably will go wrong." But I think that's, that's the best way into it.


Natalia Godyla:

Must be a strong follower of Murphy's Law.


Andrew Paverd:

Oh, yes.


Natalia Godyla:

(laughs).


Nic Fillingham:

What are you watching? What are you binging? What are you reading? Either of those questions, or anything along in that flavor.


Andrew Paverd:

I'll, I'll have to admit, I'm a, I'm a big fan of Star Trek. So I've been watching the new Star Trek Discovery series on, on Netflix. That's, that's great fun. And I've recently been reading a, a really in- interesting book called Atomic Habits. About how we can make some small changes, and, uh, how these can, can help us to build larger habits and, and propagate through.


Nic Fillingham:

That's fascinating. So that's as in looking at trying to learn from how atoms and atomic models work, and seeing if we can apply that to like human behavior?


Andrew Paverd:

Uh, no. It's just the-


Nic Fillingham:

Oh, (laughs).


Andrew Paverd:

... title of the book.


Natalia Godyla:

(laughs).


Nic Fillingham:

You, you had me there.


Natalia Godyla:

Gotcha, Nick.


Nic Fillingham:

I was like, "Wow-"


Natalia Godyla:

(laughs).


Nic Fillingham:

" ... that sounds fascinating." Like, "Nope, nope. Just marketing." Marketing for the win. Have you always been Star Trek? Are you, if, if you had to choose team Star Trek or team Star Wars, or, or another? You, it would be Star Trek?


Andrew Paverd:

I think so. Yeah.


Nic Fillingham:

Yeah, me too. I'm, I'm team Star Trek. Which m- may lose us a lot of subscribers, including Natalia.


Andrew Paverd:

(laughs).


Nic Fillingham:

Natalia has her hands over her mouth here. And she's, "Oh my gosh." Favorite Star Trek show or-


Andrew Paverd:

I, I have to say, it, it would've been the first one I watched, Deep Space Nine.


Nic Fillingham:

I love Deep Space Nine. I whispered that. Maybe that-


Natalia Godyla:

(laughs).


Nic Fillingham:

... it's Deep Space Nine's great. Yep. All right, cool. All right, Andrew, you're allowed back on the podcast. That's good.


Andrew Paverd:

Thanks.


Natalia Godyla:

You're allowed back, but I-


Nic Fillingham:

(laughs).


Natalia Godyla:

... (laughs).


Andrew Paverd:

(laughs).


Nic Fillingham:

Sort of before we close, Andrew, is there anything you'd like to plug? I know you have a, you have a blog. I know you work on a lot of other sorta projects and groups. Anything you'd like to, uh, plug to the listeners?


Andrew Paverd:

Absolutely, yeah. Um, we are actually hiring. Eh, well, the team I work with in Cambridge is, is hiring. So if you're interested in privacy preserving machine learning, please do have a look at the website, careers.microsoft.com. And submit an application to, to join our team.


Natalia Godyla:

That sounds fascinating. Thank you.


Nic Fillingham:

And can we follow along on your journey and all the great things you're working at, at your website?


Andrew Paverd:

Eh, absolutely, yeah. And if you follow along the, the Twitter feeds of both Microsoft Research Cambridge, and the Microsoft Security Response Center, we'll, we'll make sure to tweet about any of the, the new work that's coming out.


Nic Fillingham:

That's great. Well, Andrew Paverd, thank you so much for joining us on the Security Unlocked Podcast. We'd love to have you come back and talk about some of the projects you're working on in a deep-dive section on a future episode.


Andrew Paverd:

Thanks very much for having me.


Natalia Godyla:

Well, we had a great time unlocking insights into security, from research to artificial intelligence. Keep an eye out for our next episode.


Nic Fillingham:

And don't forget to tweet @MSFTSecurity. Or email us at securityunlocked@microsoft.com with topics you'd like to hear on a future episode. Until then, stay safe.


Natalia Godyla:

Stay secure.

More Episodes

5/5/2021

Ready or Not, Here A.I. Come!

Ep. 26
Remember the goodoledays when wespent youthfulhours playing hide and seek with our friends in the park?Wellit turns out that game of hide and seek isn’t just for humans anymore.Researchers have begunputting A.I. to the test by having it play this favorite childhood gameover and overandhavingthe softwareoptimize its strategiesthrough automated reinforcement training.In today’s episode,hosts Nic Fillingham and Natalia Godyla speak with Christian Seifert and Joshua Neil about their blog postGamifying machine learning for stronger security and AI models,and how Microsoft is releasing this new open-sourcedcode to help it learn and grow.In This Episode, You Will Learn:What is Microsoft’sCyberBattleSim?What reinforcement learning is and how it is used in training A.I.How theOpenAIGym allowed for AI to be trained and rewarded for learningSome Questions We Ask:Is an A.I. threat actor science fiction or an incoming reality?What are the next steps in training the A.I.?WhowastheCyberBattleSimcreated for?ResourcesOpenAIHide and Seek:OpenAIPlays Hide and Seek…and BreaksTheGame! 🤖Joshua and Christian’sblog post:Gamifying Machine Learning for Stronger Security and AI ModelsChristian Seifert’sLinkedIn:https://www.linkedin.com/in/christian-seifert-phd-6080b51/Joshua Neil’sLinkedIn:https://www.linkedin.com/in/josh-neil/NicFillingham’sLinkedIn:https://www.linkedin.com/in/nicfill/NataliaGodyla’sLinkedIn:https://www.linkedin.com/in/nataliagodyla/Microsoft Security Blog: https://www.microsoft.com/security/blog/Transcript[Full transcript at https://aka.ms/securityunlockedep26]Nic Filingham:Hello and welcome to Security Unlocked! A new podcast from Microsoft where we unlock insights from the latest in news and research from across Microsoft Security Engineering and Operations Teams. I'm Nic Filingham.Natalia Godyla:And I'm Natalia Godyla. In each episode, we'll discuss the latest stories from Microsoft Security. Deep dive into the newest threat intel, research, and data science.Nic Filingham:And profile some of the fascinating people working on artificial intelligence in Microsoft Security.Natalia Godyla:And now, let's unlock the pod.Nic Filingham:Hello, Natalia! Hello, listeners! Welcome to episode 26 of Security Unlocked. Natalia, how are you?Natalia Godyla:Thank you, Nic. And welcome to all our listeners for another episode of Security Unlocked. Today, we are chatting about gamifying machine learning, super cool, and we are joined by Christian Seifert and Joshua Neil who will share their research on building CyberBattleSim, which investigates how autonomous agents operate in a simulated enterprise environment by using high-level obstruction of computer networks and cyber-security concepts. I sounded very legit, but I did just read that directly from the blog. Nic Filingham:I was very impressed.Natalia Godyla:(laughs)Nic Filingham:If you had not said that you read that from the blog, I would've been like, "Wow". I would to like to subscribe to a newsletter. Natalia Godyla:(laughs)Nic Filingham:But this is a great conversation with, with Christian and Joshua. We talked about what is reinforcement learning. Sort of as a concept and how does that gonna apply to security. Josh and Christian also walked us through sort of why this project was created and it's really to try and get ahead of a future where, you know, malicious actors have access to some level of automated, autonomous tooling. Uh, and so, this is a new project to sort of see what a future might look like when there all these autonomous agents out there doing bad stuff in the cyber world.Natalia Godyla:And there are predecessors to this work, at least in other domains. So, they used a toolkit, a Python-based Open AI Gym interface to build this research project but there have been other applications in the past. OpenAI is, uh, well-known for a hide-and-seek. There is a video on YouTube that shows how the AI learned over time different ways to obstruct the agent and the simulated environment. Things like, blocking them off using some pieces of the wall or jumping over the wall.Nic Filingham:The only thing we should point out is that this CyberBattleSim is an open source project. It's up on GitHub and attained very much want researchers, and really anyone who's interested in this space to go and download it, go and run it, play around with it, and help make it better. And if you have feedback, let us know. There is contact information, uh, through the GitHub page but you can also contact us at Security Unlocked at Microsoft dot com and we can make sure you, uh, get in contact with the team. And with that, on with the pod?Natalia Godyla:On with the pod!Nic Filingham:Welcome to Security Unlocked, new guest, Christian Seifert. Thanks for joining us and welcome returning guest, Josh Neil, back to the podcast. Both of you, welcome. Thanks for being on Security Unlocked.Christian Seifert:Thanks for having us!Joshua Neil:And thanks, Nic.Nic Filingham:Christian, I think as a, as a new guest on the podcast, could we get a little introduction for our listeners? Tell us about, uh, what you do at Microsoft. Tell us about what a day to day look like for you.Christian Seifert:Sure, so I'm a, uh, research lead on the Security and Compliance team. So our overall research team supports a broad range of enterprising consumer products and services in the security space. My team in particular is focused on protecting users from a social engineering attack. So, uh, think of, like, fishing mails for instance. So we're supporting Microsoft Defender for Office and, um, Microsoft Edge browser.Nic Filingham:Got it, and Josh, folks are obviously familiar with you from previous episodes but a, a quick re-intro would be great. Joshua Neil:Thanks. I currently lead the Data Science team supporting Microsoft threat experts, which is our managed hunting service, as well as helping general res... cyber security research for the team.Nic Filingham:Fantastic, uh, again, thank you both for your time. So, today in the podcast, we're gonna talk about a blog post that came out earlier in this month, on April 8, called Gamifying Machine Learning for Stronger Security in AI Models, where you talk about a new project that has sort of just gone live called CyberBattleSim. First off, congratulations on maybe the coolest name? For, uh, sort of a security research project? So, like, I think, you know, just hats off there. I don't who came up with the name but, but great job on that. Second of all, you know, Christian if, if I could start with you, could you give us a sort of an introduction or an overview what is CyberBattleSim and what is discussed in this blog post?Christian Seifert:As I... before talking about the, the simulator, uh, the... let me, let me kind of take a step back and first talk about what we tried to accomplish here and, and why. So, if you think about the security space and, and machine learning in particular, a large portion of machine-learning systems utilized supervised, uh, classifiers. And here, essentially, what we have is, is kinda a labeled data set. So, uh, for example, a set of mails that we label as fish and good. And then, we extract, uh, threat-relevant features. Think of, like, maybe particular words in the body, or header values we believe that are well-suited to differentiate bad mails from good mails. And then our classifiers able to generalize and able to classify new mails that come in. Christian Seifert:There's a few, uh, aspects to consider here. So, first of all, the classifier generalizes based on the data that we present to it. So, it's not able to identify completely unknown mails. Christian Seifert:Second, is that usually a supervised classification approach is, is biased because we are programming, essentially, the, the classifier and what it, uh, should do. And we're utilizing domain expertise, red teaming to kind of figure out what our threat-relevant features, and so there's bias in that. Christian Seifert:And third, a classifier of who has needs to have the data in order to make an appropriate classification. So, if I have classifier that classifies fish mail based on the, the content of the mail but there is the threat-relevant features are in the header, then that classifier needs to have those values as well in order to make that classification. And so, my point is these classifiers are not well-suited to uncover the unknown unknowns. Anything that it has not seen, kinda new type of attack, it is really blind to it. It generalizes over data that, that we present to it. Christian Seifert:And so, what we try to do is to build a system that is able to uncover unknown attacks with the ultimate goal then to, of course, develop autonomous defensive component to defend against those attacks. So, that gives it a little bit of context on why we're pursuing this effort. And this was inspired by reinforcement learning research and the broader research community, mostly that is currently applied kinda in the gaming context. Christian Seifert:So OpenAI actually came out with a neat video a couple of years ago called Hide and Seek. Uh, that video is available on YouTube. I certainly encourage listeners to check it out, but basically it was a game of laser tag where you had a kinda, uh, a red team and a blue team, uh, play the game of laser tag against each other. And at first they, of course, randomly kind of shoot in the air and run around and there is really no order to the chaos. But eventually, that system learned that, “Hey, if a red team member shoots a blue team member, there's a reward.” and the blue team member also learned while running away from the red team member is, is probably a good thing to do. Christian Seifert:And so, OpenAI kinda, uh, established the system and had the blue team and the red team play against each other, and eventually what that led to is really neat strategies that you and I probably wouldn't have come up with. 'Cause what the AI system does, it explores the entire possible actions base and as result comes up with some unexpected strategies. So for instance, uh, there was a blue team member that kinda hid in a room and then a red team guy figured, “Hey, if I jump on a block then I can surf in that environment and get into the room and shoot the blue team member”. So that was a little bit an inspiration because we wanted to also uncover these unknown Christian Seifert:Unknownst in the security context.Nic Filingham:Got it. That's great context. Thank you Christian. I think I have seen that video, is that the one where one of the many unexpected outcomes was the, like, one of the, the, blue or red team players, like, managed to sort of, like, pick up walls and used them as shields and then create ramps to get into, like, hidden parts of the map? Uh, uh, am I thinking about the right video? Christian Seifert:Yes, that's the right video. Nic Filingham:Got it. So the whole idea was that that was an experiment in, in understanding how finding the unknown unknowns, using this game, sort of, this lazar tag, sort of, gaming space. Is, is that accurate?Christian Seifert:That's right, and so, they utilized reinforcement learning in order to train those agent. Another example is, uh, DeepMind's AlphaGo Zero, playing the game of Go, and, and here, again, kind of, two players, two AI systems that play against each other, and, over time, really develop new strategies on how to play the game of Go that, you know, humans players have, have not come up with. Christian Seifert:And it, eventually, lead to a system that achieved superhuman performance and able to beat the champion, Lisa Dole, and I think that was back in 2017. So, really inspiring work, both by OpenAI and DeepMind.Nic Filingham:Got it. I wonder, Josh, is there anything you'd like to- before we, sort of, jump into the content of the blog and, and CyberBattleSim, is there anything you'd like to add from your perspective to, to the context that Christian set us up on? Joshua Neil:Yeah. Thanks, Nic. I, I mean, I think we were really excited about this because... I think we all think this is a natural evolution of, of our adversaries, so, so, currently, our adversaries, the more sophisticated ones, are primarily using humans to attack our enterprises and, that means they're slow and they can make mistakes and they don't learn from the large amount of data that's there in terms of how to do attacks better, because they're humans.Joshua Neil:But I think it's natural, and we just see this, uh, everywhere and, all of technology is that people are bringing in, you know, methods to learn from the data and make decisions automatically, and it's- so it's a natural evolution to say that attackers will be writing code to create autonomous attack capabilities that learn while they're in the enterprise, that piece of software that's launched against the enterprise as an attack, will observe its environment and make decisions on the fly, automatically, from code. Joshua Neil:As a result, that's a frightening proposition because, I think the speed at which these attacks will proceed will be a lot, you know, a lot more quick, but also, being able to use the data to learn effective techniques that get around defenses, you know, we just see data science and machine learning and artificial intelligence doing this all over the place and it's very effective that the ability to consume a large amount of data and make decisions on it, that's what machine learning is all about. And so, we at Microsoft are interested in exploring this ourselves because we feel like the threat is coming and, well, let's get ahead of it, right? Let's go experiment with automated learning methods for attacks and, and obviously, in the end, for defense that, by implementing attack methods that learn, we then can implement defensive methods that will, that will preempt what the real adversaries are doing, eventually, against our customers.Joshua Neil:So, I think that's, sort of, a philosophical thing. And then, uh, I love the OpenAI Hide-and-Seek example because, you know, the analogy is; Imagine that instead of, they're in a room with, um, walls and, and stuff, they're on a computer network, and the computer network has machines, it has applications, it has email accounts, it has users, it's got a cloud applications, but, in the end, you know, an attacker is moving through an environment, getting blocked in various ways by defenses, learning about those blockings and detections and things and finding gaps that they can move through in, in very similar ways. So, I just, sort of, drawing that analogy back, Hide-and-Seek, it is what we're trying to do in cyber defense, you know, is, is Hide-and-Seek. And so the, I think the analogy is very strong.Nic Filingham:Josh, I just wanna quickly clarify on something that, that you said there. So, it sounds like what you're saying is that, while, sort of, automated AI-based attacking, attackers or attacking agents maybe aren't quite prevalent yet, they're, they're coming, and so, a big part of this work is about prepping for that and getting ahead of it. Is, is, is that correct?Joshua Neil:That's correct. I, I'm not aware of sophisticated attack machinery that's being launched against our enter- our customers yet. I haven't seen it, maybe others have. I think it's a natural thing, it's coming, and we better be ready.Christian Seifert:I mean, we , we see some of it already, uh, in terms of adversarial machine learning, where, uh, our machine learning systems are getting attacked, where, maybe the input is manipulated in a way that leads to a misclassification. Most of that is, is currently more, being explored in the research community.Natalia Godyla:How did you apply reinforcement learning? How did you build BattleSim? In the blog you described mapping, some of the core concepts of reinforcement learning to CyberBattleSIm, such as the environment, that action space, the observation space and the reward. Can you talk us through how you translated that to security?Christian Seifert:Yeah. So, so first let, let me talk about reinforcement learning to make sure, uh, listeners understand, kinda, how that works. So, as I mentioned, uh, earlier in the supervised case, we feed a label data set to a learner, uh, and then it able to generalize, and we reinforcement learning works very differently where, you have an agent that sits within an environment, and the agent is, essentially, able to generate the data itself by exploring that environment.Christian Seifert:So, think of an agent in a computer network, that agent could, first of all, scan the network to, maybe, uncover notes and then they're, maybe, uh, actions around interacting with the notes that it uncovers. And based on those interactions, the agent will, uh, receive a reward. That reward actually may be delayed by, like, there could be many, many steps that the agent has to take before the reward, uh, manifests itself. And so, that's, kinda, how the agent learns, it's, e- able to interact in that environment and then able to receive a reward. And so that's, kinda, what, uh, stands, uh, within the core of the, the CyberBAttleSim, because William Bloom, who is the, the brains behind the simulation, has created an environment that is compatible with, uh, common, uh, reinforcement learning tool sets, namely, the OpenAI Gym, that allows you to train agents in that environment.Christian Seifert:And so, the CyberBattleSim represents a simple computer network. So, think of a set of computer nodes, uh, the, the nodes represent a computer, um... Windows, Mac OS, sequel server, and then every node exposes a set of vulnerabilities that the agent could potentially exploit. And so, then, as, kind of, the agent is dropped into that environment, the agent needs to, first, uncover those nodes, so there's a set of actions that allows to explore the state space. Overall, the environment has a, a limited observability, as the agent gets dropped into the environment, you're not necessarily, uh, giving that agent the entire network topology, uh, the agent first needs to uncover that by exploring the network, exploiting nodes, from those nodes, further explore the network and, essentially, laterally move across the network to achieve a goal that we give it to receive that final reward, that allows the agent to learn.Natalia Godyla:And, if I understand correctly, many of the variables were predetermined, such as, the network topology and the vulnerabilities, and, in addition, you tested different environments with different set variables, so how did you determine the different environments that you would test and, within that particular environment, what factors were predetermined, and what those predetermined factors would be.Christian Seifert:So we, we determined that based on the domaine expertise that exists Christian Seifert:... is within the team, so we have, uh, security researchers that are on a Red Team that kind of do that on a day-to-day basis to penetration tests environments. And so, those folks provided input on how to structure that environment, what nodes should be represented, what vulnerabilities should be exposed, what actions the agent is able to take in- in terms of interacting and exploring that, uh, network. So our Red Team experts provided that information. Nic Filingham:I wonder, Christian, if you could confirm for me. So there are elements here in CyberBattleSim that are fixed and predetermined. What elements are not? And so, I guess my question here is if I am someone interfacing with the CyberBattleSim, what changes every time? How would you sorta define the game component in terms of what am I gonna have to try and do differently every time? Christian Seifert:So the- the CyberBattleSim is this parametrized, where you can start it up in a way that the network essentially stays constant over time. So you're able to train an agent. And so, the network size is- is something that is dynamic, that you can, uh, specify upon startup. And then also kinda the node composition, as well as ... So whether ... how many Windows 10 machines you have versus [inaudible 00:19:15] servers, as well as the type of vulnerabilities that are associated with each of those nodes. Nic Filingham:Got it. So every time you- you establish the simulation, it creates those parameters and sort of locks them for the duration of the simulation. But you don't know ... The agent doesn't know in advance what they will d- they will be. The agent has to go through those processes of discovery and reinforcement learning. Christian Seifert:Absolutely. And- and one- one tricky part within reinforcement learning is- is generalizability, right? When you train an agent on Network A, it may be able to learn how to outperform a Red Team member. But if you then change the network topology, the agent may completely flail and not able to perform very well at all and needs to kind of re- retrain again. And that- that's a common problem within the- the re- reinforcement learning research community. Natalia Godyla:In the blog you also noted a few opportunities for improvement, such as building a more realistic model of the simulation. The simplistic model served its purpose, but as you're opening the project to the broader community, it seems l- that you're endeavoring to partner with the other researchers to create a more realistic environment. Have you given some early thought as to how to potentially make the simulation more real over time? Christian Seifert:Absolutely. There is a long list of- of things that we, uh, need to think about. I mean, uh, network size is- is one component. Being able to simulate a- a regular user in that network environment, dynamic aspects of the network environment, where a node essentially is added to the network and then disappears from the network. Uh, all those components are currently not captured in the simulation as it stands today. And the regular user component is an important one because what you can imagine is if we have an attacker that is able to exploit the network and then you have a defender agent within that network as well, if there is no user component, you can very easily secure that network by essentially turning off all the nodes. Christian Seifert:So in- a defender agent needs to also optimize, uh, to keep the productivity of the users that are existing on the network high, which is currently not- not incorporated in- in the simulation. Nic Filingham:Oh, that's w- that's amazing. So there could be, you know, sort of a future iteration, sort of a n- network or environment productivity, like, score or- or even a dial, and you have to sort of keep it above a particular threshold while you are also thwarting the advances of the- of the agent. Christian Seifert:Absolutely. And I mean, that is, I think, a common trade off in the security space, right? There are certain security m-, uh, measures that- that make a network much more secure. Think of like two-factor authentication. But it does u- add some user friction, right? And so, today we're- we're walking that balance, but I'm hoping that there may be new strategies, not just on the attacker's side, but also on the defender's side, that we can uncover that is able to provide higher level of security while keeping productivity high. Nic Filingham:I think you- you- you have covered this, but I- I'd like to ask it again, just to sort of be crystal clear for our audience. So who is the CyberBattleSim for? Is it for Red Teams? Is it for Blue Teams? Is it for students that are, you know, learning about this space? Could you walk us through some of the types of, you know, people and- and roles that are gonna use CyberBattleSim?Christian Seifert:I mean, I think that the CyberBattleSim today is- is quite simplistic. It is a simulated environment. It is not ... It'-s it's modeled after a real world network, but it is far from being a real world network. So it's, uh, simplistic. It's simulated, which gives us some advantages in terms of, uh, scalability and that learning environment. And so at this point in time, I would say, uh the simulation is really geared towards, uh, the research community. There's a lot of research being done in reinforcement learning. A lot of research is focused on games. Because if you think about a game, that is just another simulated environment. And what we're intending to do here with- with some of the open source releases is really put the spotlight on the security problem. And we're hoping that the- the reinforcement learning researchers and the research community at large will pay more attention to this problem in the security domain. Nic Filingham:It's currently sort of more targeted, as you say, as- as researchers, as sort of a research tool. For it to be something that Red Teams and Blue Teams might want to look at adopting, is that somewhere on a road map. For example, if- if you had the ability to move it out of the simulation and into sort of a- a- a VM space or virtual space or perhaps add the ability for users to recreate their own network topology, is that somewhere on your- your wishlist? Christian Seifert:Absolutely. I think there's certainly the goal to eventually have these, uh, autonomous defensive agent deployed in real world environments. And so in order to get to that, simulation needs to become more and more realistic in order to achieve that. Joshua Neil:There's a lot of work to be done there. 'Cause reinforcement learning on graphs, big networks, i- is computationally e- expensive. And just a lot of raw research, mathematics and computing that needs to be done to get to that real- real world setting. And security research. And in incorporating the knowledge of these constraints and goals and rewards and things that ... T- that takes a lot of domain research and getting- getting the- the security situation realistic. So it's hard. Christian Seifert:In the simulation today, it provides the environment and ability for us to train a Red Team agent. So an agent that attacks the environment. Today, the defender is very simplistic, modeled probabilistically around cleaning up machines that have been exploited. So as kinda the next point on the wishlist is really getting to a point where we have the Red Team agent play against a Blue Team agent and kinda play back and forth and see kinda how that influences the dynamic of the game. Natalia Godyla:So Christian, you noted one of the advantages of the abstraction was that it wasn't directly applicable to the real world. And because it wasn't approved as a safeguard against nefarious actors who might use CyberBattleSim for the wrong reason. As you're thinking about the future of the project, how do you plan to mitigate this challenge as you drive towards more realism in the simulation? Christian Seifert:That is certainly a- a- a risk of this sort of research. I think we are still at the early stages, so I think that risk is- is really nonexistent as it stands right now. But I think it can become a risk as the simulation becomes more sophisticated and realistic. Now, we at Microsoft have the responsible AI effort that is being led at the corporate level that looks at, you know, safety, reliability, transparency, accountability, e- et cetera, as kind of principles that we need to incorporate into our AI systems. And we, early on, engaged the proper committees to help us shape the- the solution in a responsible fashion. And so at this point in time, there weren't really any concerns, but, uh, as the simulation evolves and becomes more realistic, I very much expect that we, Christian Seifert:... be, uh, need to employ particular safeguards to prevent abuse. Nic Filingham:And so without giving away the battle plan here, wh- what are some other avenues that are being, uh, explored here as part of this trying to get ahead of this eventual point in the future, where there are automated agents out there in the wild? Joshua Neil:This is the- the core effort that we're making, and it's hard enough. I'll also say I think it's important for security folks like us, especially Microsoft, to try hard things and to try to break new ground and innovation to protect our customers and really the world. And if we only focus on short-term product enhancements, the adversaries will continue to take advantage of our customers' enterprises, and we really do need to be taking these kind of risks. May not work. It's too ... It's really, really hard. And t- and doing and in- in purposefully endeavoring to- to- to tackle really hard problems is- is necessary to get to the next level of innovation that we have to get to. Christian Seifert:And let me add to that. Like, we have a lot of capabilities and expertise at Microsoft. But in the security space, there are many, many challenges. And so I don't think we can do it alone. Um, and so we also need to kinda put a spotlight on the problem and encourage the broader community to help solve these problems with us. And so there's a variety of efforts that we have pursued over the last, uh, couple of years to do exactly that. So, about two years ago we published a [inaudible 00:28:52] data science competition, where we provided a dataset to the broader community, with a problem around, uh, malware classification and machine risk identification and basically asked the community, "Hey, solve this problem." And there was, you know, prize money associated with it. But I really liked that approach because we have ... Again, we have a lot of d- expertise on the team, but we're also a little bit biased, right, in- in terms of kinda the type of people that we have, uh, and the expertise that we have. Christian Seifert:If you present a problem to the broader research community, you'll get a very different approaches on how people solve the problems. Most likely from com- kind of domains that are not security-related. Other example is an RFP. So we funded, uh, several research projects last year. I think it was, uh, $450,000 worth of research projects where, again, we kind of laid out, "Here are some problems that are of interest that we wanna put the spotlight on, and then support the- the research community p- to pursue research in that area." Nic Filingham:So what kind of ... You know, you talk about it being, uh, an area that we all sort of collectively have to contribute to and sort of get b- behind. Folks listening to the podcast right now, going and reading the blog. Would you like everyone to go and- and- and spin up CyberBattleSim and- and give it a shot, and then once they have ... Tell us about the- the types of work or feedback you'd like to see. So it's up on GitHub. What kind of contributions or- or feedback here are you looking for from- from the community? Christian Seifert:I mean, I'd really love to have, uh, reinforcement learning researchers that have done research in this space work with the CyberBattleSim. Kinda going back to the problem that I mentioned earlier, where how can we build agents that are generalizable in a way that they're able to operate on different network topology, different network configuration, I think is an- an- an exciting area, uh, that I'd love to see, uh, the research community tackle. Second portion is- is really enhancing the simulation. I mentioned a whole slew of features that I think would be beneficial to make it more realistic, and then also kinda tackle the problem of- of negatively impacting potential productivities of- of users that operate on that network. So enhancing the- the simulation itself is another aspect. Nic Filingham:Josh, anything you wanted to add to that? Joshua Neil:Yeah, I mean, I- I think those were the- the major audiences we're hoping for feedback from. But a- al- also like Christian said, if a psychologist comes and looks at this and has an idea, send us an email or something. You know, that multidisciplinary advantage we get from putting this out in the open means we're anticipating surprises. And we want those. We want that diversity of thought and approach. A physicist, "You know, this looks like a black hole and here's the m- ..." Who knows? You know, but that's- that's the kind of-Nic Filingham:Everything's a black hole to a physicist- Joshua Neil:(laughs) Yeah. Nic Filingham:... so that's, uh ... Joshua Neil:So, you know, I think that diversity of thinking is what we really solicit. Just take a look, yeah. Anybody listening. Download it. Play with it. Send us an email. We're doing this so that we get your- your ideas and thinking, for us and for the whole community. Because I think we- we also believe that good security, uh, next generation security is developed by everybody, not just Microsoft. And that there is a- there is a good reason to uplift all of humanity's capability to protect themselves, for Microsoft but for everybody, you know? Natalia Godyla:So Christian, what are the baseline results? How long does it take an agent to get to the desired outcome? Christian Seifert:So the s- simulation is designed in a way that also allows humans to play the game. So we had one of our Red Teamers to actually play the game and it took that person about 50 operations to compromise the entire network. Now when we take a- a random agent that kinda uninformed takes random actions on the network, it takes about 500 steps. So that's kind of the- the lower baseline for an agent. And then we trained, uh, a Deep Q, uh, reinforcement learning agent, and it was able to accomplish, uh, the human baseline after about 50, uh, training iterations. Again, network is quite simple. I wouldn't expect that to hold, uh, as kinda the- the simulation scales and becomes more complex, but that was, uh, certainly an encouraging first result. Joshua Neil:And I think the- the significant thing there is, even if the computer is- takes more steps than the human, well, we can make computers run fast, right? We can do millions of iterations way faster than a- than a human and they're cheaper than humans, et cetera. It's automation. Nic Filingham:Is there a point at which the automated agent gets too good, or- or is there sort of a ... What would actually be the definition of almost a failure in this experiment, to some degree? Joshua Neil:I think one- one is to- to sort of interpret your question as it could be overfed. That is, if it's too good, it's too specific and not generalized. And as soon as you throw some different set of constraints or network at it, it fails. So I think that's a- that's a real metric of the performances. Okay, it- it learned on this situation, but how well does it do on the next one? Nic Filingham:Is there anything else, uh, either of you would like to add before we wrap up here? I feel like I've covered a lot of ground. I'm gonna go download CyberBattleSim and- and try and work out how to execute it. But a- anything you'd like to add, Christian? Christian Seifert:No, not from me. It was, uh, great talking to you.Natalia Godyla:Well, thank you Josh and Christian, for joining us on the show today. It was a pleasure. Christian Seifert:Oh, thanks so much. Joshua Neil:Yeah, thanks so much. Lots of fun. Natalia Godyla:Well, we had a great time unlocking insights into security, from research to artificial intelligence. Keep an eye out for our next episode. Nic Filingham:And don't forget to tweet us at MSFTSecurity, or email us at securityunlocked@microsoft.com, with topics you'd like to hear on a future episode. Until then, stay safe. Natalia Godyla:Stay secure.
4/28/2021

Knowing Your Enemy: Anticipating Attackers’ Next Moves

Ep. 25
Anyonewho’severwatched boxing knows that great reflexes can be the difference between achampionshipbeltand a black eye.The flexing ofan opponent’s shoulder, the pivot of theirhip-a good boxer will know enoughnot only topredictand avoidthe incoming upper-cut, but willknow how to turn the attack back on theiropponent.Microsoft’s newestcapabilities in Defender puts cyber attackers in the ring and predicts theirnext attacks as the fight is happening.On today’s episode,hosts Nic Fillingham and Natalia Godyla speak with ColeSodja, Melissa Turcotte, and Justin Carroll(and maybe even a secret, fourth guest!)abouttheirblogposton Microsoft’s Security blogabout the new capabilities of using an A.I.to see the attacker’s next move.In This Episode, You Will Learn:• What kind of data is needed for this level of threat detection and prevention?• The crucial nature of probabilistic graphical modeling in this process• The synergistic relationship between the automated capabilities and the human analystSome Questions We Ask:• What kind of modeling is used and why?• What does the feedback loop between program and analyst look like?• What are the steps taken to identify these attacks?Resources:Justin, Melissa’s, and Cole’s blog post:https://www.microsoft.com/security/blog/2021/04/01/automating-threat-actor-tracking-understanding-attacker-behavior-for-intelligence-and-contextual-alerting/Justin Carroll’s LinkedIn:https://www.linkedin.com/in/justin-carroll-20616574/Melissa Turcotte’s LinkedIn:https://www.linkedin.com/in/mturcotte/ColeSodja’sLinkedIn:https://www.linkedin.com/in/cole-sodja-a255361b/Joshua Neil’s LinkedIn:https://www.linkedin.com/in/josh-neil/NicFillingham’sLinkedIn:https://www.linkedin.com/in/nicfill/NataliaGodyla’sLinkedIn:https://www.linkedin.com/in/nataliagodyla/Transcript[Full transcript at https://aka.ms/SecurityUnlockedEp25]Nic Fillingham:Hello, and welcome to Security Unlocked, a new podcast from Microsoft, where we unlock insights from the latest in news and research from across Microsoft Security engineering and operations teams. I'm Nic Fillingham.Natalia Godyla:And I'm Natalia Godyla. In each episode, we'll discuss the latest stories for Microsoft Security, deep dive into the newest threat intel, research and data science.Nic Fillingham:And profile some of the fascinating people working on artificial intelligence in Microsoft Security.Natalia Godyla:And now, let's unlock the pod. Welcome, everyone, to another episode of Security Unlocked, and hello, Nic, how's it going?Nic Fillingham:It's going well, good to see you on the other side of this Teams call. Although, you and I were in person not 24 hours ago. You were here in Seattle, we were filming some more episodes of the Security Show. I don't think we've really given listeners of the podcast a full, meaty introduction to the Security Show, have we? Do you wanna let listeners know what they can find?Natalia Godyla:We play games and hang out with experts in the industry and we've done everything from building robots with folks, to building blocks, to painting our nails. You can find the Security Show on our YouTube channel, so, YouTube.com/MicrosoftSecurity or you can go to aka.ms/securityshow. We talk with Chris Wysopal, the CTO and co-founder of Veracode on modern secure software development, and Dave Kennedy, who comes to talk to us about SecOps and everything you need for a survival kit in SecOps, so come come check them out.Nic Fillingham:Bad news is you, you have to deal with, uh, Natalia and I on another, uh, media format. But before you go there, make sure you listen to today's episode of Security Unlocked. We have a couple of returning guests. We have Cole and Justin, who have been on before, as well as Josh Neil, who comes on in the, in the last few minutes. And new guest, Melissa. They're all from the Microsoft 365 Defender research team, and they all co-authored a blog from April 1st called Automating Threat Actor Tracking, Understanding Attacker Behavior for Intelligence and Contextual Alerting, which is exactly what it is but I think it buries the lead. Natalia, you had a great TL;DR, what did they do?Natalia Godyla:The team used statistics to predict the threat actor group and the next stage in the attack and really early in the attack, so that we could identify the attack and inform customers so that they could stop it. I think what's really incredible here is, not only the ability to predict that information, but to just do it so early in kill chain. Nic Fillingham:Within two minutes after an attack begin, using this model, Microsoft threat experts were able to send a notification to the customer to let them know an attack was underway. The customer was able to do, you know, the necessary things to get that attack shut down. We'd love, as always, your feedback. Send us emails, securityunlocked@microsoft.com. Hit us up on the Twitters. On with the pod. Natalia Godyla:On with the pod. Nic Fillingham:Well, welcome back to the Security Unlocked podcast, Cole and Justin, and welcome to the Security Unlocked podcast, Melissa. Thanks for joining us today. We have three wonderful guests, with maybe a, a fourth special guest appearing at the end. And today we're gonna be talking about a blog post appearing on the Security blog from April the 1st, called Automating Threat Actor Tracking, Understanding Attacker Behavior for Intelligence and Contextual Alerting. All of the authors from that blog are here with us. Cole, if I could start with you, if you could sort of reintroduce yourself to the audience, give us a little bit, uh, about your role, what you do at Microsoft, and then perhaps hand off to one of your colleagues for the next intro.Cole Sodja:Sure. Will do, thank you. So, hi, I'm Cole. I work in the Microsoft 356 Defender group. I'm a statistician. Primarily my responsibilities are driving, kind of, research and innovation in general, with supporting threat analytics, threat hunting, threat research in general. Yeah, been doing that for about three years now, and I love it, and I that's a little bit about myself, I'll hand it over to Melissa. Melissa Turcotte:All right. My name's Melissa, I work with Cole, so in the same group, Microsoft 365 Defender. I'm also a statistician by background. I've been in the cyber domain for about probably seven years now. I was working for Department of Energy research laboratory in their cyber research group for five years, and I joined Microsoft a year ago. I like all sorts of problems related to cyber. My expertise probably would be in anomaly detection, but anything related to cyber, and there's data in a problem, I like to be involved.Nic Fillingham:And Justin.Justin Carroll:Hey. I also work in the Microsoft 365 Defender team, doing threat intelligence. My main focus is uncovering new threats and actor groups and understanding what they're doing, different modifications to how they're conducting their attacks, and the outcomes of those attacks, and then figuring out the most effective ways to either, communicate that out to customers or action on detection capabilities to stop them from succeeding.Nic Fillingham:Listeners of the podcast will note that you have a super sweet ninja turtles tattoo, is that correct? Justin Carroll:This is accurate, this is definitely accurate. Nic Fillingham:And, and we may or may not have a super secret fourth guest on this episode, who may join us towards the end, who you would, you would know from an very early episode of the podcast, but perhaps we'll keep them secret until the very end. Thank you all for joining us, thank you for your time. Again, we're referring to a, a blog post that, that all of you authored from April 1st. This is a, quite a complex, and, and sort of technical blog post, which I know a lot of our audience will love. Nic Fillingham:I got a little lost in the math, but I, I absolutely was enthralled by what you all have undertaken here. Cole, if I could start with you, can you give us, give us an overview of what's covered in this blog post, and sort of what this project was, how you tackled it, and what we're gonna talk about, uh, on this episode today.Cole Sodja:Yeah. So if I step back, being someone kind of still fairly new in learning, uh, to cyber security, uh, I approached things pretty much with just using data, right? Doing data driven imprints, as I'd say. And through my research, what I started to, um, kinda ask myself is, can we kinda get ahead of cyber security attacks, you know, from a post-breach perspective? Once we see an adversary in a network, can we start to make some predictions, basically, on what they're likely gonna do? Who is the adversary, or is it human operated, is it an automated script, for example. And then if we recognize the adversary, kinda recognize their tactics, their techniques, their procedures, can we say, okay, we're, we're likely gonna see they're gonna ransom this enterprise, for example.Cole Sodja:So I tried to look at it as more of a data mining exercise initially, it's like, can I recognize these type of patterns, and then how predictive are these patterns that we're seeing in terms of what likely is gonna occur. Or put it another way, what type of threat is this, essentially, to the enterprise? So, so that's kinda the background, the motivation. Now, when I started this project, back with Justin and then with Melissa, it started really as let's look for particular, uh, threat actors that we're aware of, that we recognize, that we know about, and see, like, can we start, from a data perspective, classifying okay, is it this group, is it that group, and what does this group tend to do? Cole Sodja:And one of the challenges in that is, is sparsity. Basically, we don't have a lot of labels sitting around out there saying, it's threat actor group A, B, C, D, and so on. We have handfuls of those. Some of these actors, they don't tend to do attacks very frequently, right? They're extremely sparse. So, so one challenge of this, and one the motivation is, how can we actually partner with threat intelligence, for example, and our threat hunters, to try and essentially encode or extract some of their information to help us build models, to help us reason over the uncertainty, essentially. Cole Sodja:And when we say probabilistic modeling, that's what we mean. It's how do we actually quantify this uncertainty, both in what we believe about the actors, or the adversaries in general, as well as what they're gonna do, right, once they've breached your network. So that's kinda how it started, and what this blog's really about is kinda giving a walk-through, essentially, of what we did initially with this research. It started with, and Justin will talk about this in a moment, it started with looking at few, select threat actors that are very serious. Cole Sodja:We started to understand their behaviors more and more and we thought it was a good opportunity, initially, to try and build a model to, again, understand what they're doing, track what they're doing, because they do change their tactics over time, as well as just see if we could get ahead of them. Can we actually notify a customer in advance, before, uh, for example, their organization's ransomed? So, so that's one part of the blog that we'll discuss, and I'll hand it over to my good friend Justin to take it from here.Justin Carroll:So, like, one of the, the main challenges that we kinda face in the intelligence sphere is understanding the particulars of an actor and when they are present in an environment. A lot of times, you'll see the intelligence is really focused on a very particular indicator such as, like, a known IP address that's malicious, or a single behavior. But it's kinda difficult to frequently pivot them out to understand when a suspected attacker is in an environment. A lot of that is due because they don't always do the exact same behaviors when they are compromising... Organization or device. There will be some variation and it basically requires manual enrichment a lot of the times of devices to try and understand the specifics of the attacks and what Justin Carroll:... the final outcomes o- wh- out of that attack, so this opportunity presented one to work with data scientists to, like, really supercharge our efforts so that we could kinda come in understanding a much bigger picture and knowing, essentially, what behaviors that we saw occur and then which ones we might suspect. A lot of times with these human operated ransomware ones, the time to alert, to notify of the expected outcome is often fairly short, in particular with, uh, one of the ones that we worked on to kinda test this method out. We had seen very short instances from time to compromise to ransom, so, um, this was to try and see if we could have a, a highly confident method of enriching that intelligence, um, and then working with other teams to get those alerts out.Natalia Godyla:If I could jump in here for a moment. So, at the beginning of your description, you noted that typically you'd use manual enrichment. Can you talk a little bit about that? So prior to this probabilistic model, how did you go through that manual enrichment process to try to, uh, predict what threat actors they were or determine what stage of an attack it was?Justin Carroll:It would be something along the lines of, let's say, you had intelligence from either a partner team or open source intelligence that says, you know, "These threat actors are using this IP address as part of their attack," and then looking for the presence of that and then finding out what actually occurred on those devices to understand the entirety of the attack, or looking more generically and saying, like, "Okay, we know these attackers like to use a particular behavior as part of their credential theft," and then so looking for all sorts of instances of that credential theft and then kinda continuing to pivot down into one that is leading to the behavior that y- you're looking for. One of the difficulties that you'll see in particular with this and other actors is, like, they will use multiple shared open source tools and payloads. Um, many of them aren't even malware, they're clean tools with legitimate purposes, so it can make it difficult to try and suss out the ones from malicious versus administrative use, so you have to look for that combination of different behaviors to indicate something malicious is afoot.Nic Fillingham:Justin, if I look at the blog, I think it might be the first chapter here, there's a MITRE ATT&CK framework diagram, Figure One, and it, uh, outlines sort of the steps taken here for how this model was able to, with high confidence, identify the, the actor and, uh, send an alert to the customer who was able to shut it down. I wonder if you could sort of, could you walk us through this, these sort of six steps as an example of, of how this work, how this worked in, in sort of real life?Justin Carroll:Yeah. I can walk through basically from a model's perspective, essentially, how it works. Timing, that's more a function of, like, how the attack, uh, typically progresses with this actor. Technically speaking, what the model's really doing is it's encoding each behavior we have, in this case, each MITRE technique in particular in terms of what's the confidence that once we see, for example, initial access follow... Under, let's say, RDP brute force, followed by lateral tool transfer with subset of tools recognized, that particular sequence right there, that's where the model would be like, "Okay, the probability that it's this particular threat actor group conditional on those two things occurring in sequence will be X," and that sequence could occur in a matter of minutes or even days and weeks, dependent on the actor, of course, we're talking about. Justin Carroll:With the, the actor we're showing in this graph, this actor typically will penetrate a network through RDP brute force, but then w- sometimes the, they won't immediately transfer their tools. They might wait a day or two, or sometimes they'll, they'll do it very fast, like, once they basically compromise a log-in then, uh, they'll, they'll go to that machine, there might be some, um, discovery related commands before they transfer or they might just transfer their tools and then that will be the attack box, basically, in which they stage their attack, and then they'll do some additional things.Justin Carroll:So at each step, basically, or each stage of the attack, as we like to call it, the model is basically gonna then update its probabilities and say, "Okay, based on all the information I've seen up to this stage, the probability that it's this actor is P and now, conditional that it's this actor with probability P, the probability that we'll now see, for example, defense evasion and this 'tack will be Q," or, or we could even go further in the attack stage to say, "Now, given all this, what's the probability that we'll see, for example, ransomware or inhibit system recovery in the coming hour? Or in the coming, you know, X time?" Justin Carroll:So the model's able to do that, but it's primarily conditional on the stages it's observed up to a point in time, not so much in terms of the time it takes for the actors to do X.Natalia Godyla:So, in this blog and in our discussion today, we're gearing up to talk about probabilistic graphical modeling as a way to address the challenge that, Cole and Justin, you've set up for us today, and, and for any of our listeners who'd like to follow along in the blog, the blog is titled "Automating threat actor tracking: Understanding attacker behavior for intelligence and contextual alerting" and you can find it on the Microsoft Security blog. I'd love to dive into the probabilistic graphical modeling and perhaps start with a definition of what that means. So, M- Melissa, could you give us an overview of this approach?Melissa Turcotte:Yeah. We have this problem which what they are essentially saying is, we have a collection of things which... I'm a statistician so I often call them variables, but, you know, features, if you will, if that's m- more easy for you to understand, but we, th- these TTPs, th- right. The sets of things that the actors are doing, and we have a collection of them. And given some collection of these, we wanna make a statement about whether or not it's ransomware or whether it's not a specific threat actor, or a group of actors. Right? And this is, this is, like, a perfect, um, example of where probability can help you make these decision, and one thing I'd like to stress is that no one of these features gives you enough information about whether or not it's this actor or this, this group of actors, or it's ransomware, you know, whatever your variable interest is.Melissa Turcotte:It really is the collection of these together that, you know, kind of in Justin's mind, as an analyst, he's, he's making these connections in his head, and I wanna be able to replicate that in some sense, I wanna take into account his knowledge and kind of his decision making process, combined with the data that I have, to make these probabilistic statements about what I think is happening. And graphical models are really great here, probabilistic graphical models in particular, as they kind of provide this joint probability distribution over all these features, and the variable of interest, in this case, is kind of, maybe is it this actor, but not necessarily. I mainly wanna know something about any one of these other features. I may already know it's this actor, and I may wanna be like, "Wh- what are the common things I see this actor do?"Melissa Turcotte:So, so graphical models really shine in this case where you have this collection of things that you are observing, and you kind of want to ask questions about any subset of them. Given some observations of others, and so th- this is a really great tool to use in this setting, and it's also quite interpretable. So if you kind of look, if you're looking at the blog and you see this Figure Two, which is a toy example, but y- you kind of, as a human, you can look at that and you can kind of understand that, "Okay, so I'm seeing transfer tools and lateral movement are related." Um, and you can kind of understand sort of wh- what the relationships the model is making. Um, and so that kind of provides this extra, you know, benefit of this in that, yeah, I can talk an analyst through what this kind of is showing and then i- it's quite interpretable for them even if they don't understand the underlying maths, and that's kind of something we really wanna strive for. Um, you shouldn't have to understand the underlying maths to kind of understand the decisions that are being made.Melissa Turcotte:It's really attractive in this sense, and then the Bayesian networks, why I really like it is kind of, the Bayesian paradigm is... So you, you have, you know, statistics, generally, or data science, you have some data and you're kind of, you know, making inference given the set of data to make statements about things of interest. So the data tells you something about your beliefs and the state of the world, but you have your own subjective beliefs about wh- what you think could and could not happen. The, the Bayesian paradigm kind of combines those two things, so it's, you have your beliefs and then you have what the data is telling you, a- and your ultimate kind of predictions are based on the combination of those things. And generally, the, the way it works is the more data you have, the data will always win through.Melissa Turcotte:So this problem, bringing it back to attacker prediction, is a case where we don't have a lot of data, right? We don't... Companies get attacked... Or we say, companies get attacked all the time but not at the scale at which we collect the underlying data, so like, you know, we have, you know, you as a user are performing actions, logging into computers you use... You know, this shows up in the data thousands of times a day, whereas an attack happens kind of, like, on a monthly scale, so c- the scales of attacks to the data we're getting is just really small, and then when you go into attacks that kind of we've labeled as being attributed to a threat actor, I mean, that's even way smaller. So it's, it's kind of a small data problem, uh, in terms of the number of labels you have.Melissa Turcotte:But what we do have is this analysts who have spent years tracking these people and have their kind of, you know, beliefs about what they do and how they changed over time. And so we Melissa Turcotte:Wanna capture that. We definitely want to include the evidence we see and the data, but we wanna capture that really rich knowledge that we get from the analysts. And so kind of that's where the Bayesian network part becomes attractive because it, it provides a very principled way to, to capture the analysts' expertise, combine that information with the data we're seeing to make these ultimate predictions.Natalia Godyla:For our audience, could you really quickly describe a Bayesian network?Melissa Turcotte:So, a Bayesian network is a way of building a model for a collection of variables whereby the idea is that you have different variables which are related to each other. It, it, it kind of helps draw out or show what those relationships are so, like, in the graph, you know, if there's an arrow from impact... Or from transfer tools to impact that's saying if I see transfer tools, that has a direct impact... I'm gonna use the word impact twice here. Has a direct impact on whether or not I'm going to see impact. So, so it's kind of the way the variables relate to each other and the way the probabilities change according to those relationships. And so a Bayesian network encodes all this information. Nic Fillingham:If I can take another swing at that one... Thank you, Melissa. I'm wondering what were some of the other, uh, techniques that you either considered for this approach? Like, did you experiment with other methods and then ultimately chose Bayesian?Melissa Turcotte:Yes, um, in fact, uh, so the initial kind of... The perhaps most obvious thing to do is to c- to think of decision trees, right? You s- you're, you're, you're seeing, you know, these things over time. Okay, I saw, um, what was the first one? Initial access with this... You don't go as broad as initial access, but I saw initial access using this, you know, minor technique. And so you can kind of think, like, you, you, you have a tree that's kind of... Okay, I saw this, I didn't see this, but I saw this and I didn't see this, so now I think it's this actor. But kind of where this is preferable is the fact that, as Paul says, we don't want to see the whole attack happen before we make a statement about what we think it is. And Bayesian networks work really well in, in the absence of some observed variables. Cole Sodja:Yeah, I'll just quickly chime in. I agree with Melissa. So, I did experiments, for example, with several models including decision trees. Even, um, different forms of Bayesian decision trees like BART for example. And in addition to what Melissa is saying where, for example, predicting the probability that it's threat actor conditioned on certain variables we saw, uh, we might also, as Melissa pointed out, want to say, okay, let's predict, for example, that this threat actor is going to do impact or a certain form of impact. And with decision trees, that means basically you're building multiple decision trees to do that. You can't just build one decision tree... Well, let's put it this way. You can't easily build one decision tree to have multiple target variables. That's something you get for free with the Bayesian network. Another thing I'll say in addition to what, um... To marginalization is the Bayesian network is more general. So, it could actually handle kind of a broader graphical structure. The decision tree is a specific graph. Cole Sodja:So, it kind of already inhibits you, if you will, to learning a certain structure over the data. Whereas the Bayesian nets, they could give you a little more general structure. We could also build these models that are time dependent, what are called dynamic Bayesian networks. That's something much harder to do with tree models. So, it's just a more flexible model as well as I would say. In my experiments, the Bayesian network did perform better on average than the set of decision trees I considered.Nic Fillingham:I'd like to better understand the relationship between this model and folks like Justin. So, is Justin, as a very experienced threat analyst, is Justin helping you define labels and helping you sort of build some of the initial... I'm, gonna get the taxonomy wrong here, so please correct me. But the initial sort of properties of the model? Or is, is Justin, as an analyst, interpreting what you sort of think you have in the model? How, how do I understand the relationship between the analyst and, and how they're providing their expertise into, into this model?Melissa Turcotte:All three.Nic Fillingham:Oh, great. (laughs)Melissa Turcotte:All three things you said is actually correct. So, so hopefully we, we've explained it somewhat well. So, yes. The first stage, right Justin? The analysts are providing us our label data. So, yes. That's the first thing. And then they also help us kind of, you know, you have the raw data, but that's kind of... There's so much data processing that goes... That, that happens before it's kind of... This data's kind of in this tabular forms that's like, yes, we... You know, these are the features we are tracking, so think of your TTPs, the different notes in your graph. Getting the data into that, kind of that schema, the threat analysts help with. So, you know, help define what, what these tactics, techniques, and procedures are that we should track. Like you said, you, you can't be super broad. Lateral movement doesn't really have a lot of meaning, um, to kind of like the different ways in which someone can do lateral movement and how granular w- you want to go. Melissa Turcotte:So, we discuss with the analysts all the time to kind of build up, you know, the ontology, if you will. And then, you know, as a first stage, like I said, it's a small data sample, so we're like... Justin helps inform what the model thinks about in a probabilistic sense. So, you... One thing I might ask him, I, I would be like... If I saw net... you know I'm borrowing from our toy example, but if I saw a network scanning modify system process, transfer tools, but didn't see any of the others, do you think it would be this actor X? Or do you think it would be ransomware? And he would be like, hmm, I would probably 60% certain. I can take that information and encode that directly so that, in the absence of any data, the model would return 60%. It would... If I didn't see any data, it would return what Justin believed was the probability in the presence of a certain number of variables. Melissa Turcotte:And then we kind of see data and we update our beliefs over time based on that. And then, also, after we've kind of trained these things, I go back to Justin and say does this make sense to you? So, he, he's kind of involved in all three, the whole process.Nic Fillingham:Melissa, I think you're telling me you've built a virtual Justin. Melissa Turcotte:We... That, that is what we are literally trying to do. And back it up... And, you know, and back it up with data as well. I'd, I'd like to like... You know, I'm a firm believer that everyone has their subjective beliefs, Justin has beliefs as well. Oftentimes, I can prove analysts wrong. Be like, they think something, I'm like, well, the data is telling me something else. So, we need to figure out, you know, that discrepancy. But, yes. We are essentially trying to build virtual Jus- uh, Justins. Although, like, th- there... I don't think there's any stage upon which we won't need the analysts to constantly feed back in with the new information they have. Nic Fillingham:Got it. And then can it come full circle? Justin, how do you as an analyst, how do you get smarter and better at what you do by what this model is, is telling you? What's the feedback loop look like here for you?Justin Carroll:It's one of those where, basically, using the model kind of super-charged my abilities where, instead of having to look at this very granular kind of like ad hoc, oh, this may be interesting, now I have the instances already serviced to me, and I have a good understanding of what success rate through the kill chain the attacker was able to get. And maybe figure out which ones that I needed to enrich more to understand was there data that we can add into the model because they've done something different that we need to capture and then look for opportunities in that way. So, really, it's basically... It made it where, give or take, sometimes it would take anywhere from 10 to 20 minutes sometimes to try and figure out, like, is this who I think it is? And like, what have they done? What are their goals? To just looking at the result from the model. And within usually seconds, being like, yeah, that looks exactly right. That's... It's confirmed, I think that's spot on. Natalia Godyla:So, Justin, was there something that was the most surprising in working with this model? Something that the model taught you either about threat actors or any details about the features? Justin Carroll:One of the things was kind of reexamining My confidence levels on different parts of the attack. Um, where Melissa was stating, for instance, you know, the data suggesting this and the models coming to this conclusion, uh, you know, thinking that it's this probability, and there would be times where I'd have to kind of reevaluate and think, like, hmm, I might've been missing something or overestimating the prevalence of a particular thing and saying it's related to such. Like, uh, I can tend to get very biased based on my narrow scope of the attacks that I'm looking at and think that it's related to this thing, but the model was able to provide a lot of clarity to some of the behaviors that maybe I didn't think were as confident a signal or extremely confident signal and I wasn't giving them the appropriate weight. That's one of the advantages of using it to understand what the attacker's doing, is I let it do much of the leg work once everything's kind of coded in. And then occasionally, like if we found opportunities where it was like, hmm, this still isn't quite right, then it could be tuned as a c- um, as necessary. Justin Carroll:I think that was probably one of the biggest ones of kind of trying to work through and actually spell out, like, my own thinking processes when I'm evaluating the data. It was something that you just kind of do without thinking, where you're constantly, as an intelligence analyst, looking at data and making conclusions on that data. But you're not usually saying, like, okay, I saw this so I'm gonna give it a 60% probability that it's this. And like, you're, you're just kind of sometimes it's either gut intuition or working on it that way. But actually having the model encode and return back what it was understanding made a, a pretty big impact in trying to understand how my own decision processes work and basically how best to kind of think Justin Carroll:About these different, wide array of attacks that we're constantly investigating.Nic Fillingham:The types of indicators that you're building this model on, again please correct me on my taxonomy here, but you're not looking for, you know, NFO files or like ASCII art or, you know, the actual threat actors name being sort of hidden somewhere in the jpeg that they drop as a, as a for the LOLs, like, they're... You're not looking for a sort of a literal signature of these threat actor groups, you're, you're, what you're, what you're doing is you're, you're seeing the actions that have been taken and without any other way of attributing them to an individual group, you're piecing them together. Nic Fillingham:And as you, as you get more actions and you piece them together based on the, the labels that you get from people like Justin, you're able to, to ultimately have a high probability that it's this threat group actor and they're doing this thing and they're likely to do this thing next. Have I got that right? You're, they're... In no way shape or form are you actually finding a secret text file that has the name, you know, the, the, the handles for all the hackers who are doing it for the LOLs.Cole Sodja:So let me just quickly jump in, you pretty much nailed it. I'll say this, so, we wanted to do both actually, right, because we don't want to restrain the model if it's, if core's gonna add predictive power, so like you said, we're not actually searching, grepping for example, for a threat actor name and some file or image, certainly not that level. But, for example, some of the actors, maybe they have common infrastructure, maybe they use particular types of tools in their attack typically, right? Like, maybe there's a SHA-1 out there they've used a lot in their attack, or, or recurring IP addresses they use as part of brute forcing. Cole Sodja:Those are there, but those are very specific and if you just relied on those, like Melissa was saying, either one or a few of those, you're not gonna generalize. You'll probably miss that attacker, right? But we certainly don't want to exclude it from the model because, um, if we happen to see that, the model will, uh, come back with a different type of probability, right? It'd be like, okay. Now the model might be more confident early, rather than waiting to see how the rest of the kill chain progresses. On the more general side, we probably won't go to the MITRE categories, 'cause they're a little too general, right? But if we go to some of the sub techniques, we don't actually have to look at the particular types of executables, or tools, or IPs used. Cole Sodja:Sometimes just the timing and sequencing is enough actually, to narrow down to, maybe not a particular threat actor, but a group of actors or, more generally, we can say with high competence, you know, this is a human adversary. They're taking this amount of time to do discovery commands, they're, they're doing lateral these type of ways. And the model could recognize that, even without knowing the particular commands, it's just seeing the more general techniques involved, right? So we do a bit of both, actually. We tend to want to rely more on, kind of, the general attacks or indicators as you're saying, that's right. But, we certainly don't want to throw away specifics that are reuse because we could get ahead of the attack much earlier too. So it's a bit of both at the end of the day.Melissa Turcotte:So yes, Nic, if, if, if you have an evil bit, look for the evil bit. You don't need data science for that. Nic Fillingham:(laughs)Natalia Godyla:And how is this model being used today, meaning is this a model that's being used by our internal security team to protect Microsoft and its customers, is it being used by a Microsoft threat experts group or is this actually embedded in some of our solutions today, and our customers are feeling that benefit? And what is the future intent of the model?Justin Carroll:One of those... So, there are multiple uses that are in place for the model. So one of the big things for me, so in my own selfish interest, it's intelligence, it's one of the easiest ways that I can keep tabs on the attacker and continually build new profiles and understand, basically, reports out, this is what they're doing, this is how they're doing it, this is how active they are. Like, are we seeing, you know, large volumes of their attack, are they taking a break, that kinda stuff. Then, the Microsoft threat experts are using it as a signal to help understand attacks early on in the kill chain so that they can get those notifications out ideally before the ransom, which can be quite difficult a lot of the times depending on the adversary and how quickly they seek to ransom. A lot of times there isn't a great deal of time.Cole Sodja:Yeah, there's other products, for example, M365D. So, um, there are plans, uh, it requires some engineering, ultimately, because this is a big product, um, huge customer base and so on. But there are already plans in motion to take what we've built already, as part of this framework, and integrate that into that product. There's other products as well, both from a threat intelligence perspective, and possibly kind of from SOC alerting perspective as well, that I'm in active discussions with other products across Microsoft to do the POC, make sure it works with their data, make sure they're comfortable and then work with their engineering team to at least get that in the plan. Those are ongoing discussion but M365D does have, kinda, I'll say, in their planning cycle, to get this in the product. Nic Fillingham:I wonder if this might be a good time to bring our secret special guest on microphone, Josh, if you're there, I think I might ask, uh, might wonder if you could jump in on this one. I think you've understated the power of what you've built here. From everything that you've just explained, you know, within a couple of minutes of a threat actor getting initial access to have a high probability index to be able to contact the customer and say, here's who we think is inside your network, here's what we think they're gonna do next, so they can shut it down. This is the next level, right? And, and Josh, when we interviewed you on episode three, you were hinting at this, if I'm not mistaken. Is this, is this sort of what you guys have been working on?Joshua Neil:Yeah, I'm so proud that we, that we took it from concept to realized value for the customers and, and at this point we've had that impact with your customers in stopping human operations. And, and so it's really exciting and, and it's, it's on the journey but, you know, if I extract an overall theme from this, it's consistent with that podcast that we had before because I was sort of complaining about AI. And I was sort of complaining about what we see in some of the, in some of the branding and marketing that, that folks do in, in cyber security. And I think this team and, and the work they've done exemplifies the right applications of data driven methods. Joshua Neil:There is no magical, artificial intelligence today. What there is is, and this is a, an experience that all of us on the data science team have had over the, over the past few years, and really for me about 20 years, is we can use data and some mathematics and some computing to begin to automate and accelerate what the humans are doing. And so, by sitting very closely with, and working very hard with the human experts like Justin, we're explicitly encoding their knowledge into models. So that's one thing is that the data science we're doing is to automate some of the stuff they're doing today. But the intention is not to solve the world, not to give our customers a license to solve security, we're, we're not gonna be able to do that. What we are able to do is uplift the sophistication of our customers operations. Joshua Neil:So, you know, what Justin sort of reflected on, uh, he's able to do a more interesting job, a more sophisticated job, because we're taking the data and his knowledge and encoding it and accelerating and automating some of the stuff that he's having to do manually now. And that's where the real nuts and bolts, you know, and the real rubber meets the road here, is that there's no magic gun that's gonna blow away all the adversaries with, with AI. What there is is hard work between data scientists and threat expertise to uplift their capabilities and accelerate their effectiveness in the face of the adversary. And that's what I would like to get across to the, to the listeners, is that by hard work and careful and close collaboration between data science and threat expertise, that's how we really make progress in this space.Nic Fillingham:Thank you so much Josh. And I just wanted to quickly clarify, from a previous comment from Cole, so this model is in use now, correct? Folks like Justin, Microsoft threat analysts, they are using this model now to make the model better, and to be able to get that additional information and those confidence levels in, in, in doing their analyst work. And so Microsoft threat expert customers are directly benefiting from this work, as of today. That's correct, is it?Joshua Neil:That's correct. We've sent targeted attack notifications to customers based on this model.Nic Fillingham:You've all been very, very, generous. Natalia Godyla:Thank you for that. And, and thank you to the whole team here for joining us on the show today. Melissa Turcotte:Absolutely.Cole Sodja:My pleasure.Joshua Neil:It was a lot of fun as always. And, and thank you, Nic and Natalia for this.Natalia Godyla:Well, we had a great time unlocking insights into security, from research to artificial intelligence. Keep an eye out for our next episode.Nic Fillingham:And don't forget to tweet us at MSFTSecurity or email us at securityunlocked@microsoft.com with topics you'd like to hear on future episode. Until then, stay safe...Natalia Godyla:Stay secure.
4/21/2021

Below the OS: UEFI Scanning in Defender

Ep. 24
All of us have seen– or at least, are familiar with – the antics of Tom and Jerry or Road Runner and Wile E. Coyote. In each one the coyote or the cat set up these elaborate plans to sabotage their foe, but time and time again, the nimble mouse and the speedy birdareable tooutsmart their attackers.In our thirdepisode discussing Ensuring Firmware Security,hosts Nic Fillingham and Natalia Godylaspeak withShweta JhaandGowtham Reddyabout developing thetoolsthat allow for them to stay one step ahead ofcybercriminals in the cat & mouse game that is cyber security.In this Episode You Will Learn:• Thenewcapabilities within MicrosoftDefenderto scan theUnified Extensible Firmware Interface (UEFI)• How theLoJaxattack compromised UEFI firmware • How UEFI scanning emerged as a capabilitySome Questions that We Ask:• Has UEFI scanning always been possible?• What types of signals is UEFI scanning searching for?• What are the ways bad actors may adjust to avoid UEFI scanning?Resources:Shweta Jha’sLinkedIn:https://www.linkedin.com/in/jhashweta/Gowtham Reddy’sLinkedIn:https://www.linkedin.com/in/gowtham-animi/Defender Blog Post:https://www.microsoft.com/security/blog/2020/06/17/uefi-scanner-brings-microsoft-defender-atp-protection-to-a-new-level/NicFillingham’sLinkedIn:https://www.linkedin.com/in/nicfill/NataliaGodyla’sLinkedIn:https://www.linkedin.com/in/nataliagodyla/Transcript[Full transcript can be found at https://aka.ms/SecurityUnlockedEp24]Nic Fillingham:Hello, and welcome to Security Unlocked, a new podcast from Microsoft where we unlock insights from the latest in news and research from across Microsoft's security, engineering, and operations teams. I'm Nic Fillingham-Natalia Godyla:And I'm Natalia Godyla. In each episode we'll discuss the latest stories from Microsoft Security, deep dive into the newest threat intel, research and data science.Nic Fillingham:And profile some of the fascinating people working on artificial intelligence in Microsoft Security.Natalia Godyla:And now, let's unlock the pod.Natalia Godyla:Hello Nic. Welcome to Episode 24. How's it going with you today?Nic Fillingham:Going well, thank you, Natalia. Yes, uh, welcome to you and welcome to listeners to Episode 24 of Security Unlocked. On today's podcast, we speak with Shweta Jha and Gowtham Reddy from the Microsoft Defender for Endpoint engineering team about capabilities in MDE to scan down into the UEFI layer. Now this is the third of three conversations we have that started back in Episode 11 with Nazmus Sakib where we talked about secure core PCs and, and firmware integrity. Then in Episode 14 we spoke with Peter Waxman about the Pluton processor and some of the new work that's happening there to imbed more security tech into sorta silicon onto the actual CPU die itself. And today we're sort of rounding that conversation out with Shweta and Gowtham to talk about how Microsoft Defender for Endpoint can now scan down or can scan down into the UEFI layer. You're gonna hear a bunch jargon, a bunch of technical terms like, I guess, UEFI. That's, we, we could start there.Natalia Godyla:Yes. And UEFI is the Unified Extensible Firmware Interface, so it is the software interface that lies between an operating system and firmware, and is an evolution of BIOS. And we'll also talk about MosaicRegressor which, for those of you that don't know, is the second ever UEFI rootkit which was discovered in 2020, but was used in an attack against NGOs in 2019. And, and for me, the timeline is shocking, second ever in the past year. Normally we hear about the continuous increase of a certain type of attack over the years, and here we're just at the second ever.Nic Fillingham:Yeah. It's a real interesting part of the conversation where we talk about the history of BIOS attacks, firmware attacks, UEFI attacks, and to learn that this has been sort of traditionally a pretty challenging area for attackers to, to breech and compromise. But, you know, Shweta and Gowtham have been, you know, very much ahead of the curve and, and being ahead of, of attackers in, in being able to develop these new capabilities to, from the operating system, scan down to the UEFI layer and look for malware, look for compromise. And it's a, it's a fascinating conversation. Again, it's sort of a completion of three episodes starting with Episode 11 and 14. So if you haven't listened to those, I recommend you add them to the queue. But I guess on with the pod.Natalia Godyla:On with the pod.Nic Fillingham:Welcome to the Security Unlocked podcast. Shweta Jha and Gowtham Reddy, welcome both of you. Thanks for being here.Gowtham Reddy:Thank you.Shweta Jha:Thank you so much for having us. We're so very excited.Nic Fillingham:I'm very excited, too. Now this is gonna be the third conversation in a sort of a mini series that we're running here on the podcast. We started with Nazmus Sakib who introduced us to the idea of secure core PCs and we talked about some of the challenges of firmware integrity and keeping firmware safe. Then we spoke Peter Waxman in another episode to learn about Pluton, the history of, of that technology and sort of what's coming for the Pluton processor. And today we're actually gonna talk about some new capabilities, or newish as of 2020, in Defender to scan down into the UEFI layer. Before we jump into to all that, let's just do some introductions for the audience. Shweta if we could start with you. Who are you? What is your role? What do you do day-to-day at Microsoft? Tell us, what you like the audience to know about you?Shweta Jha:Absolutely. Thank you, Nic. My name Shweta Jha. I am a program manager with Microsoft Defender for Endpoints, and I've been building security solutions features and products, and I'm super excited about it because security is the need today for our, uh, customers. And a few of the features that I built with my team were part of anti-tampering. Investment that we did, EDR block as part of be able to blocking and containment. And then we are gonna talk a lot about UEFI scanner. So pretty much around building security solution and features in this team and helping our customers.Nic Fillingham:Fantastic. And, and Gowtham, welcome to the podcast. If you could also introduce yourself. Uh, tell us about your role. What does your day-to-day look like?Gowtham Reddy:Hi. This is Gowtham Reddy. I'm an engineering manager in Microsoft Defender, uh, Endpoint. So before engineering manager, so I was working as an engineer in the same team for last six years. So I work on, uh, many of the rootkit technologies, the Defender, uh, has and, uh, the remediation technologies to remediate many of the malwares that are present on the system. I have been where I working on this fantastic team, developing like durable protection features that were, and compliment the ever changing malware fields.Nic Fillingham:That's great. So, again, welcome to both of you. Thanks for your time. One of the things we do on the, uh, Security Unlocked podcast here is we, we don't necessarily cover the latest announcements. We, we sort of look back over the last sort of three to six months for interesting sort of technology, interesting advancements in, in security technology, and we bring experts on to, to talk about these new features and capabilities after them sort of being in the wild. Today we're talking about the UEFI scanning capabilities that are in Microsoft Defender, and there's a blog post that, that both of you helped author back in, in June of 2020, which feels like a decade ago, but I guess it's more like six or seven months. So I wondered if one of you might be able to just walk us through. What was that announcement made in that blog post? What was sort of the news? And then I think maybe if the other one or maybe just following, I'll, I'll leave it to how we, how we split this up. But what was announced back in June? And sort of what's happened since then? How have those new capabilities sort of rolled out and what are we seeing with customers actually using them?Shweta Jha:So I, I guess I can get us started, and then I'll hand it over to Gowtham definitely to talk more on the technical details and the, the attacks that we see in the wild, and that's why we kind of built this UEFI scanner. So as you understand, this is a journey, right? We built a layered defense in that security solutions. And when we build any security solution, we need to make sure that we take a holistic approach. So if you look at the operating level of security solutions, we've been getting pretty great at operating level security solutions. And it's not only Microsoft. If you see other security providers as well, they have been doing great, too.Shweta Jha:So what does that mean? It means that because the operating system level security solution is really great, it does making difficult for attackers to not get detected at that level. It's a constant battle, so they have been looking into other means where they can go into the system undetected, and that's where if you look at the data, you would find that in recent past the attacks across hardware and firmware level has been on the rise. So we built UEFI scanner keeping in mind that we should be able to detect those type of attacks, because those type of attacks are not only very dangerous, but often time they are not detected. They persist even if you reboot the system. So the nature of these type of attacks is very dangerous, and keeping that in mind, we decided to build UEFI scanner.Gowtham Reddy:So I can add like why we did, uh, build the UEFI scanner. So because of the operating system security features that Microsoft is constantly working on, the bad guys are trying to go in, down and down in the layered architecture. And so some of the traits of the ia64 went onto the BIOS, tampering the BIOS and, uh, tampering the MBR, the master board required and, uh, VBR based bootkits. So Defender has evolved into that space of counting the MBR and, uh, detecting the bootkits and the boot time. Gowtham Reddy:So as a logical evolution the bad guys are, uh, from the stage of Colonel to the MBR, MBR to the UEFI. So we were anticipating that this kind of evolution is quite possible and the UEFI implants were not very far. So that's the time we found the first UEFI implant called LoJax. So that was a triggering point when we completely committed to ourselves to expand our root kit technology, to detect any kind of rotates presence in the UV. So that was our core idea of expanding or rotating to the layer much below the operating system. So there were some challenges Natalia Godyla:If you don't mind me jumping in, I had a question around that. So...Gowtham Reddy:Mm-hmm (affirmative)Natalia Godyla:... the way you're framing it is that when we started to notice the threat landscape moved to this layer, we decided to invest in this type of technology. What about the technology itself? Had there always been this opportunity to tackle UEFI scanning, or is there something new that we're leveraging in order to solve this problem Now that might not have been around beforehand? Gowtham Reddy:That's a good question. So there was always a chance to exploit the UEFI, but it's about the timing of the attackers to get at target this space because the rest of the platform and ecosystem is getting more and more secure. So the UEFI is not new. So it was there a decade ago, but the implants are new because of the advances in the operating system. Nic Fillingham:So Gowtham, tell us about the LoJax attack that happened. Was it the first or it was one of the first detected compromises of the UEFI firmware? Can you tell us some more about, about that? If folks aren't familiar with it like me? Gowtham Reddy:Mm-hmm (affirmative).So that definitely some theoretical researcher driven, before the LoJax, but the LoJax is a fast known exploitation instance where we know we found it in the wild. It is quite possible even before that a UEFI implant demonstrated in many of the black hat conferences, but those are theoretical in nature. So the research had access to the device and they demonstrated it. But LoJax's is the one where from operating system level. So a particular malware, I would say it as a root kit, which has tried to intrude from kernel mode to the UEFI, and they have installed a UEFI driver. So if we consider the operating system as a drivers, even the firmware itself had some drivers. So they were able to install a driver which actually in turn drops the another kernel mode driver, advanced operating system boots up. it's about the boot sequence. Gowtham Reddy:So first the firmware starts running and it initializes all the system, and then it invokes operating system. So in the LoJax's case, after the firmware is completed, it has already dropped the kernel driver on the operating system, if it is not present. So that means by the end of the firmware sequence, so we have a presence of a kernel driver. And when that kernel driver starts, that is a user mode, malware starts, kicks in. So this keeps repeating even after you were re-install the wares, even if you change the hard disc, the same pattern will be fought. So that's how the LoJax's type work. Nic Fillingham:And I wonder, do we know, what was the breakthrough that made LoJax possible? UEFI has been around for a while. UEFI for probably predates LoJax. And obviously before UEFI, there was sort of the more standard sort of BIOS that probably most folks are familiar with. Can we talk a little bit more about how LoJax came about and sort of what maybe changed or what the breakthrough was on the attacker side? Gowtham Reddy:I would say that there were a couple of open source read-write drivers, which has a capability to access the firmware, using a special interface called SPI. SPI is a something called serial peripheral interest. So using the serial peripheral interface, any kernel driver can instruct the platform hardware layer to read and write any content in the flash. So I think like many of the security industry knows a driver called a read drive, everything, they call it as RWE. So this is the driver using which anybody can read any offset, any device memory, and write. I think this is, the prevalence of this kind of open source tools might be help attackers to develop this kind of ecosystem of all the sequence of the malware, the root kits. Shweta Jha:In addition to what Gowtham said, definitely the work that researchers were doing in this space, it always starts with researcher trying to do something and then attackers trying to find other means. So here are the things. Attackers usually do exploit things that are not done in a right way. So in this case, for example, if there are certain configuration that you need to, or your partner needs to make sure that those are in place, for example, rewrite where you are not providing writing access, just the reading access, and so on. Shweta Jha:So typically in all these type of attacks would see that misconfigured devices are exploited the most, and that misconfiguration happens at the time when the devices are getting built. So that is another factor why these attacks are very successful, because there are misconfigured devices, because while building the devices, somebody messed to configure it and right way. And if you look at the journey, that's where you have a secure core PC, which is designed be secured, making sure that the things that are needed to protect the computer against these types of attacks that are there out from the first day. Natalia Godyla:So my question is about the application of this new technology. So I really appreciate you walking through that attacker workflow. So what type of signals is UEFI scanning, looking for? What is it using to enrich the context of the existing end point data?Gowtham Reddy:That's a very good question. So basically the level of details that UEFI scanner can get is enormous. So this is the area where like the defender has a content scanning. So, uh, we have, uh, extended our content scanning to every file that is present inside the firmware. So this help the defender research to write any kind of content scanning signatures to detect any bad content. So that means in this case, if research knows any implant, so we have a capability to scan the 600 million devices to know if any of our customers have impacted with the specified malicious file. Gowtham Reddy:And this is just one part of our UEFI scanner. And the other part of it is detecting any anomalous behavior inside the firmware. For example, in many of the supply chain attacks like Solarigate, it's quite possible that some of the OEMs channels were compromised and the deliver the firmware updates with the malicious modules in it. Gowtham Reddy:So in this case, our UEFI scanner collects all the metadata about the new for- firmware update and we run heavy amount models in our cloud. And that will tell us if there is an unknown anomaly that exists in this particular firmware update. Instead of a known malware implant so that the UEFI scanner has the two capabilities. One is detecting a known malicious implant, and the other one is anomalous from where presence of a fax. So in this case, we act both ways. Nic Fillingham:What does an anomaly look like in this context? Gowtham Reddy:Anomalies look like, for example, if you have a firmware is a, firmware is a file system, like a typical drive. A presence of an driver file, probably a hedge P driver file or an unsigned driver file. On a Dell OEM is constrained to the anomaly. Because we have trained the model of all the known Dell firmwares with them, a ML model. So any new image with the unexpected file, it will be immediately flagged. Nic Fillingham:And why is ML the sort of approach you've taken here versus sort of heuristics? I would have thought that there's a pretty limited set of content. They could make up sort of firmware and firmware instructions. Obviously, I don't know anything about this space, so I'll caveat that there, but, um, could you talk about why ML versus heuristics versus something else?Gowtham Reddy:In the days of, uh, BIOS, so you are a expectation was right. The bast consists of a series of micro code, Gowtham Reddy:... which is, uh, very limited. And, uh, in the context of UEFI, you have a full file system, uh, which has, like, uh, thousands of files; individual files. And, uh, this causes... Uh, creates, uh, basically a huge amount of, uh, the vectors space, which to scan or to collect the metadata. Gowtham Reddy:So it's not just simple collection of mecra- microcodes. It contains the drivers, it contains the services, it contains a lot of other things. It's a file system like NTFS.Nic Fillingham:Got it. So because UEFI is, as you say, a file system as opposed to... What was BIOS? BIOS was not a file system? BIOS was, uh, sort of a discreet, sort of, low level executable?Gowtham Reddy:Yeah, i- i- it is just a sequence of, uh, microcode instructions that will be run on the firmware. So basically, i- it has a s- uh, fi- se- set of microcodes. Nic Fillingham:So the machine learning models that you reference, w- where are they running? Are some of them running locally? Are they all running in the Cloud? Is it a mixture of the two?Gowtham Reddy:They're all running in the Cloud for now. So we have MDATP Cloud services where we run all this clo- uh, demo models. So our models are really very effective. So recently, we got in, uh, so- so, uh, the UEFI alert by, uh, mal- model. Apparently, it's a kind of, um, true positive because, um, there was a Microsoft engineer who was working on a hardware space.Gowtham Reddy:So he take, uh, firmware. And he kept a developer driver and he flashed on his own device. And, uh, our UEFI scanner immediately caught it and we... the security administrator got an alert and there was an investigation happen. So we are pretty ready to catch any kind of such things now.Natalia Godyla:So we all know it's a cat and mouse game with the threat actors. So what is the team anticipating in terms of how the actors will adjust their processes to evade this new UEFI scanning technology?Gowtham Reddy:That's a good question. We're trying to validate something in a- a lower level of trust, the lower level of ring other than the kernel. So definitely, there is a chance that attacker can modify the firmware presence. Uh, he can spoof the content when defender tries to scan. So this is quite, uh, possible. But we are already working on mitigating that kind of an attacks. Nic Fillingham:So now that this feature, these capabilities, have been live in the product for, uh, I guess over six months at this point, w- what have you learnt? What have you seen in the telemetry? What have you seen in the types of attacks and, I guess, even sort of false positives that have- have come through from- from this new, uh, capability?Gowtham Reddy:Uh, that's a very good question. So we learnt a lot of things. The UEFI file system has never scanned before. So we got some false positives on the content that we scan but we immediately fine-tuned our signatures.Gowtham Reddy:Back in... Six months before, when we published a blog, we only know the first UEFI known implant called LoJax but often we share... There was a second implant called Public. That's called MosaicRegressor and our UEFI scanner has well detected the MosaicRegressor implant. Uh, the- the telemetry count was small. So we did, uh, able to detect the mi- MosaicRegressor.Nic Fillingham:So in this first six months, as well as the LoJax campaign, uh, what's the taxonomy here? How do we f- refer to it?Gowtham Reddy:Uh, we can consider... W- we are, uh, tracking them as an UEFI implant malware or UEFI rootkit. So this is the category we are looking at. So right now, we have, uh, LoJax and we have a MosaicRegressor as, uh, two big families in this space.Nic Fillingham:Big families. Got it. Shweta Jha:Yeah, about MosaicRegressor, I wanted to add a little bit more just to complement what, uh, Gowtham mentioned, how powerful this tool is. And how powerful this particular feature is. So if you read through the MosaicRegressor, uh, breach, it was a nationwide targeted attack.Shweta Jha:This was targeted for diplomats. And this attack, as Gowtham described, first they would insert one module. Uh, that one module would get undetected and then that module would try to do other stuff, like try to, uh, get in touch with command and control and get another, uh, module and so on.Shweta Jha:So the entire c- chain is so very interesting. And I'm glad that we built this feature and we were able to detect it because it's so powerful. Most of the security solution, they're not able to detect because they don't have this, uh, such great capabilities.Shweta Jha:But look at the way this attack was carried. It was pretty much targeted, pretty much nationwide for a few countries, originated from one country. So the sophistication level in the nature itself speaks for it and I'm glad that we, as in our product, we have this capability which can even, you know, unknown, first seen, it can detect those type of attacks as well.Natalia Godyla:In the process of developing this new technology, where were there false starts? What techniques did you try but didn't work to solve this problem?Shweta Jha:Little bit on the journey, right? We have been working on it. Um, so Gowtham explained about how we have rootkit, bootkit level and then we went to the UEFI site and we had to be extremely careful because it's, like, uh, it has a high integrity and high severity of going wrong.Shweta Jha:So we had to be very careful making sure that the running system is not damaged and at this point, I'll hand it over to Gowtham because he can explain, in detail, each and every pieces that we took into consideration to making sure that our customers' device remain intact. So go ahead Gowtham.Gowtham Reddy:Yeah. Thanks Shweta. So, uh, we have indeed explored, uh, many mechanisms like accessing the PCI space from the operating system itself, which we didn't continue to proceed because of some of the pushback from the kernel team to update the haul.Gowtham Reddy:So actually, uh, to accessing any peripheral device from the PCI bus, there are a couple of complications because the peripherals have, uh, specific implementation of Reads and Writes, the bus Reads and Writes. So, uh, the approach we took was, uh, using the SBI interface, which is pretty much, kind of, an, uh, universal interface which is developed by Motorola by a long time ago.Gowtham Reddy:So luckily, what worked in our favor was most of the Intel p- s- uh, chipsets, they support the SBI based access. So they support the SBI, uh, using which we can use the memory map mechanisms to access the PCI space.Gowtham Reddy:So basically, here, what happened was instead of directly using the hardware primitives, we used, uh, software primitives because the chipsets are well supporting the SBI interface. So that's how we landed in our approach. Nic Fillingham:I wanted to circle back to the use of machine learning here in- in solving this problem. How big are the signal sets that you're getting to train the model? How big is the model?Nic Fillingham:Is the model that you use here, to detect anomalies in the firmware layer, is it as sophisticated and large as something as, like, looking for malware on endpoints? Or are we talking, like, a much sort of smaller more, sort of, n- nuance. No, that's not the right word. Sort of a smaller bespoke model?Gowtham Reddy:Uh, I can take that question. So u- usually, uh, in the endpoint when- when applying the malware, um, in machine learning models, we heavily focus on the individual file properties, like file headers, file footers and some file p- properties and so on. Gowtham Reddy:But UEFI case, we built a brand new machine learning model based on the properties of the UEFI image itself. So thanks to David, from our MDATP team. So he come up with a model where... which takes input signals as specific to the UEFI firmware image.Gowtham Reddy:To give some examples, each firmware drive has a lot of GUIDs, called firmware GUIDs. And then they have some properties called, uh, file types and properties. Every property that we took was specific to the firmware. So they are not generic to the specific malware files that we see regular malware detections. So these are highly tailored to the signals from the UEFI firmware image. Nic Fillingham:And were you able to reuse some of the anomaly detection Nic Fillingham:Algorithms are purchased from other parts of the defender engineering org, or did you have to sort of build a brand new model and a brand new way to detect anomalies? Shweta Jha:Yeah. So, we definitely used our existing infrastructure. So, as you know? Uh, we have a massive backend system where we get tons of signals and we run tons and tons of AI and ML model to detect the anomalies and to detect the new trends and so on. So, as Gordon was talking, for this particular UV, AI and ML model, even though where we had to tweak it to make sure that we capture the inputs that are UV specific, the models were used, the pipeline to collect the data that were used and the channel where we surface it to our customers. So, if you look at the end to end story, the way we do things are we detect, we remediate, and we also notify to our SecOps that, "Hey, these are the things that happened in your environment." And that goes in the form of alerts or incidents and so on. So, we used exactly same infrastructure, same pipeline, but specific to UV. Natalia Godyla:So, I know a little earlier in this episode, we talked about the learnings after being in market. What about the impact to SecOps teams? Do we have any early numbers to talk through about what this has raised for our customers? Shweta Jha:That's a great question. We do see here and there, though the number is not pretty high on the implant, but we do see in numbers there, like, as Gordon mentioned about a mosaic regression. We did find that and there are few others also. But I think the most important aspect of this unique feature is that, just a little bit forget about this feature and see that today's world, today, there is no UV scanner, the security admins or SecOps, they, they don't know what is happening at this level. They have tons of device in their organization. And these devices are at this level is completely black box for them, because they don't know whether it is configured well. They don't know if there are implants there. They don't know if there are vulnerabilities that could be exploited. Shweta Jha:So, there's the power of this UV scanner. One is, you know, so we, we built a solution keeping in mind that we will not only detect, we will bring these, these things where they don't have visibility today to understand what is going on. So, the focus area, and then the objective that we have is to detect the implant, either using the heuristic detection or the AI, ML but also read through each and every configuration that are happening at this level and the vulnerabilities that exist at this level and bring that to the, SecOps attention, so that when they look at it, they can take appropriate action to remediate it. So, that's the next step. And that is the work right now, we are currently doing. We do not have, in the form of report, we do see it in our data and we want to make sure that these are available to our SecOps. But just to tell you, there are tons and tons of misconfigured device out there. And it's, it's a little tricky.Gowtham Reddy:To add more about the misconfiguration. So, it's about like the PC settings, like a UV, the BIOS read-write or whatever the settings we'll use to see in when we go to the BIOS in the past. So, the UV must be configured well to support the secure boot, to use the TPM and to use any of the hardware provided features, it must be configured well. If it is misconfigured, you won't get any protection. So, if you have a helmet in your backseat, when you are driving, it won't help you. So, you had to keep it on your head. Shweta Jha:(laughs). That's a great analogy. Nic Fillingham:That leads us to, what is the guidance here for Sec admins and security teams out there? How do they enable this functionality? Is it on by default in, in certain places? What do we need to do to make sure that, that customers are getting the full protection from this capability? Shweta Jha:So, uh, this, this feature is enabled by default on all the devices. Um, we made sure that this is available. And the great news is that it is not only, you know, Windows 10, it is available for servers, download as well. So, that's the power that we have in our solution. Ultimately, if you look at what is the future that are gonna look like, secure core PC is the future we should be heading towards. But because enterprises and customers are not there yet, uh, we have UV scanner to compliment it. The other thing, if we have to talk about the futuristic roadmap, right now, we built the scanner for UV, but there are other network devices like network adapter and things like that. There is a scope to extend these types of capability to those devices as well, because those, there is a possibility to get those devices exploited too. So, that's something we are considering to work through. Nic Fillingham:Got it. So, just to confirm there, so, this new capability is on by default in any device that is being protected by the defender service. Is, is it, is it as simple as that or is there sort of more to it?Shweta Jha:Yes. Any device which is having defender antivirus running.Natalia Godyla:Thank you for that. That was super helpful. And thank you both for joining us on the show today. Shweta Jha:Thank you, Natalia. It was pleasure to be here and talking with our customers. Thank you so much for hosting us. Gowtham Reddy:Thank you Natalia and Nick for hosting us. So, it's been wonderful time talking to you about UV scanner. Thank you so much. Nic Fillingham:Thank you both for your time. Thanks for bringing great innovation to the security space. Shweta Jha:Absolutely. It's a constant journey and we're on it. Natalia Godyla:Well, we had a great time unlocking insights into security from research to artificial intelligence. Keep an eye out for our next episode. Nic Fillingham:And don't forget to tweet us @msftsecurity or email us @securityunlocked@microsoft.com with topics you'd like to hear on a future episode. Until then, stay safe.Natalia Godyla:Stay secure.