# The STRIDE Controversy: Evolution vs. Extinction in Security Models

URL: https://securitytable.ai/the-stride-controversy-evolution-vs-extinction-in-security-models/
Published: 2024-11-13
Duration: 2471 seconds
Season: 2
Episode: 32
Hosts: Chris Romeo, Izar Tarandach, Matt Coles

## Show notes and chapters

We discuss a controversial LinkedIn post claiming "Threat Modeling is Dead." While the STRIDE methodology may need updating, it remains a valuable "gateway" tool for teaching security concepts to developers without security backgrounds. We discuss how STRIDE serves as a useful categorization system, emphasize that dogmatic approaches to threat modeling are problematic, and argue that what matters most are results rather than strict adherence to any particular methodology. Our conclusion; STRIDE is still alive and relevant, but it could benefit from an update to demonstrate its continued applicability.

Follow AI Security Table:

➜ Home: [https://securitytable.ai/](https://securitytable.ai/)

➜ X: [https://x.com/AISecurityTable](https://x.com/AISecurityTable)

➜ LinkedIn: [https://www.linkedin.com/company/ai-security-table/](https://www.linkedin.com/company/ai-security-table/)

➜ YouTube: [https://www.youtube.com/@AISecurityTable](https://www.youtube.com/@AISecurityTable)

## Transcript

**Izar Tarandach (0:09)**: Sponsor us, you will see me drinking with my finger up.

**Chris Romeo (0:15)**: So how many espressos do you drink a day now?

**Izar Tarandach (0:19)**: How many are possible?

**Chris Romeo (0:23)**: So this episode of Security Table brought to you by Isar's espresso machine, which I don't know what brand it is. But it appears to be making him very happy, and it can make you very happy too. And then Matt was showing a slightly bigger cup.

**Matt Coles (0:37)**: Wait, slightly bigger?

**Chris Romeo (0:38)**: And look at these. Ours is like a mini. No, his is like half the size of that.

**Izar Tarandach (0:42)**: It's not the cup, it's the coffee.

**Matt Coles (0:45)**: It's the, it's the, it's the, it's tapered. Go on, it's smaller. Look, he's, he's drinking it properly too with his finger.

**Chris Romeo (0:55)**: It's so funny to watch him. He's like so distinguished. He's like This is, this is good, old chap.

**Izar Tarandach (1:01)**: For distinguished, I have to go with my monocle.

**Chris Romeo (1:05)**: I mean, yeah, the pinky has to go all the way out at that point. $1 million.

**Matt Coles (1:15)**: Just don't do that while you're drinking.

**Chris Romeo (1:17)**: Be funny if you could do both. See if you can combine both together. Okay, Quell, enough fun with this. We do have a purpose. We are here for a reason. And we're going to talk about a post somebody made on LinkedIn called Threat Modeling is Dead. Let me just read it. Why don't I read it to set the stage? It's shorter.

**Izar Tarandach (1:40)**: Was it threat modeling that was dead?

**Chris Romeo (1:41)**: That's what it says.

**Izar Tarandach (1:42)**: I'm going to read it.

**Chris Romeo (1:42)**: It actually says threat modeling is dead. Direct quote to put this on the record so that the audience knows what we're talking about here. The post in bold says threat modeling is dead. And then Stride has not aged well. I've seen firsthand the thick PDFs and Excel files that my clients have had delivered to them by consultants. Those docs have about a million data flow diagrams, giant tables with columns spanning over multiple pages, and a bunch of unactionable data. Software engineers and hackers both move much faster than in the past. I don't even know what this, I'm not gonna comment. A list of high-level threats is not really useful when it comes to agile secure software development because exploitable attack vectors are usually down in the weeds. It's the detail that's missing from STRIDE reports despite the huge amount of documentation. What can we do instead? ATT&CK modeling. I've been favoring ATT&CK modeling over threat modeling for some time now. It has only 3 steps. Analyze attack surface for each component of the design. Produce an attack register, a list of potential attacks against the exposed attack surface. Produce a list of associated security controls to mitigate the attacks. ATT&CK modeling cuts the documentation significantly and produces relevant actionable data with none of the fluff. Another bonus, the attack register can be used as a scope for the pen test. And that is the setting. Where to begin?

**Izar Tarandach (3:05)**: Where to begin?

**Matt Coles (3:10)**: I don't know where you do. Where do you want to begin with that? Because there's so many, so much wrong with that statement.

**Izar Tarandach (3:14)**: Wait, wait, wait, wait. I think that I'm personally going to start with, with Acadia. Because I did put a comment there in that post. And I have in the past in this here podium and podcast declared that DAST is dead. Exactly. At the same time when we did declare that, we did this coming from places where we are users of it and we have seen it in many places and we have seen the results and how they're used. And at the same time, in that same episode and many times after, we did say that it still has its uses. So we went for it's dead with a bit of a flair for the drama. But in this year post, my comment there was that I would love for people who declare things to be dead to at least take their polls beforehand, because I think that stepping out and saying, hey, one of the things that's like the most popular and that people use as a huge onboarding tool to get behind this chat modeling thing is that when so many people are actually using it every day and making good use of it and teaching it and learning it and I don't know. I think that perhaps we should be a bit more careful with the things that we declared dead. Could just be my age talking, but perhaps check before.

**Chris Romeo (4:53)**: Well, he's saying threat modeling is dead. That's a pretty big statement.

**Matt Coles (4:59)**: It is. And then on top of that, to go ahead and actually suggest an alternative threat modeling approach as a replacement.

**Izar Tarandach (5:07)**: Look, it's dead clearly because we already solved all the possible problems. So there's no more need for truck modeling. Everybody's doing the right thing. So yeah, clearly it's dead.

**Chris Romeo (5:17)**: Yeah.

**Matt Coles (5:18)**: AI's gonna solve everything, right? I mean, come on.

**Izar Tarandach (5:20)**: AI does—

**Matt Coles (5:20)**: No, AI won't solve everything.

**Izar Tarandach (5:21)**: AI already did solve.

**Chris Romeo (5:23)**: So I mean, let's, let's, let's pick this apart a little bit more. So he says Stride has not aged well. Okay, great. That's your opinion. We can, we can leave that on the table. But then he says, I've seen firsthand the, the PDFs and Excels delivered by consultants with million, a million, about a million data flow diagrams. That's probably an exaggeration. I don't think anyone ever sent a million data flow diagrams in a document. I kept giant tables with columns and a bunch of unactionable data. I, I, I got a, an idea for you here. You might be using the wrong consultant if that's the data that they're sending to you. Like, you could apply that to anything. If someone's doing a home inspection for a new home I'm buying and they drive up with a pickup truck with 1,400 boxes in it and unload them and say, that's your inspection report, I think I'm going to probably find a new home inspector, right? Like, I'm not going to parse through 1,400 boxes of paper to see what you think was wrong with the house I was going to buy.

**Izar Tarandach (6:19)**: You forgot the most important part. The guy driving with the 14 boxes has a cousin who's a contractor and can fix each and every one of them. Okay? So I think that Albert Anhai has a great comment in the post where where he points out that there is such a thing as, uh, what's it that he call it, the consultant, uh, industrial complex.

**Matt Coles (6:42)**: Mhm.

**Izar Tarandach (6:44)**: And this person's clearly a victim of that.

**Matt Coles (6:47)**: I mean, you've talked about, you've talked about it for, for years now about, you know, having a consultant parachute in, give, give a bunch of stuff and leave, you know, each just the seagull, the seagull consult.

**Izar Tarandach (7:01)**: Consultant, they swoop in, shit on the table, leaves, and you have to clean that mess.

**Matt Coles (7:09)**: And so if you're paying your consultants by, you know, but for the words, then, you know, you're gonna get what you get. Uh, but, but I mean, that's a, that's a, that's a using— was it hyperbole for, for opening of argument? Uh, is kind of, is very disingenuous. So starting with threat modeling is dead, STRIDE is not aged well. To, to hide, to say that, so first off, there's probably some confusion about what STRIDE is versus what threat modeling is, right? STRIDE, of course, is a, is a, has been seen, I think, or has been popularized as a methodology for performing threat modeling, which relies on DFDs. And in practice, that's the way it's been implemented. STRIDE on its own is really just a categorization of threats and that there's a process of looking at whatever diagrams or models or descriptions of a system you have to match those things to threats, to the threats in STRIDE.

**Chris Romeo (8:18)**: Yeah.

**Matt Coles (8:18)**: And, and so to say that threat modeling is dead and STRIDE does not age well, if you're using STRIDE to categorize threats, then you're still doing threat modeling. And, and I guess the other, I guess the other important part here is to consider that what we call threat modeling, for people who are not watching this or who are listening to this, go to YouTube and watch this, this video. So what we call threat modeling, I think, has, has evolved over time. Traditionally, threat modeling was looking at threats, purely threats. What was somebody going to, what is somebody going to do to your system? More importantly, what is somebody looking to do to your system? Meaning what impact or effect do they want to have, right? Do they want to do site defacement? Do they want to, you know, spoof your data? Do they want to sniff your data on the wire? What threats exist? But over time, I think that has evolved and the term threat modeling is now used to cover, as an umbrella term to cover things like looking at threats and attacks. And of course, so what is an attacker going to do to cause a threat to occur or to, to implement a threat? And what weaknesses or vulnerabilities are they going to leverage to make those attacks possible? And so threat modeling looks at weaknesses today. Threat modeling looks at weaknesses, vulnerabilities, attacks, and threats. Informs risk. We've talked about this at length in the past, right, about informing risk. And so threat modeling as an activity, I'll even go on a limb, and I know some of our audience will be happy about this, is we should not use threat modeling as a term. Maybe just, we should call it secure design review and be done with it.

**Izar Tarandach (10:05)**: Will we?

**Chris Romeo (10:06)**: Please no.

**Izar Tarandach (10:07)**: Review?

**Chris Romeo (10:08)**: Yeah, review is a different— secure design is one thing. Secure design review sounds like a crappy meeting I got to sit in for 2 hours where too many people want to talk.

**Matt Coles (10:17)**: Sure.

**Izar Tarandach (10:18)**: Come up with a better term.

**Matt Coles (10:19)**: Come up with a better term if you want, but that's fine. But threat modeling is fine.

**Izar Tarandach (10:22)**: Security design roast.

**Chris Romeo (10:24)**: Yes. The roast of your secure design.

**Matt Coles (10:28)**: Critical design analysis.

**Chris Romeo (10:31)**: Is that what you said? We come up with microphones and we say mean things about you and your design. I love this idea.

**Matt Coles (10:35)**: Shall we call it a critical design analysis? And that maybe is a better way. Critical? That sounds so crazy. It does sound too critical.

**Izar Tarandach (10:42)**: Things we would have liked you to think before you did them.

**Matt Coles (10:46)**: The T, yeah, put that in after number 4.

**Chris Romeo (10:48)**: The T, B, C, C before. Can't even think of what it is, but coming back around to Stride though. So I may have an, I may, I don't know, I may have a slightly unpopular opinion of how I use Stride that you guys, I don't know if you guys are going to agree with this or not, but to me Stride is a gateway. Not gateway computer, because that's from a long time ago.

**Izar Tarandach (11:10)**: Yeah, we talked about that.

**Matt Coles (11:10)**: Not a gateway drug. With Kestrel.

**Chris Romeo (11:12)**: It's not a gateway drug either, but it's a gateway to threat modeling, right? And the way I've always approached it is Stride is a way to teach people to, in the very early days, to threat model when they don't have the security knowledge experience. I think what this post is missing is the reason why Stride exists. You can't take this attack modeling idea and hand it to somebody, a developer who doesn't have security background. They don't have all that stored in their head. And using their, your scanning tool as the source for the things they need to think about, why the heck do I need to do that? Why don't I just run the scanning tool? Why don't I just run Burp with its different attacks?

**Matt Coles (11:48)**: Because you have to have code already that's already functioning and you're really late. Wait, well, let's not go back to that episode about you're really late in the process.

**Izar Tarandach (11:57)**: But wait, wait, wait, there is one thing here that's important. I think that Okay, no, I don't think, I agree with you that STRIDE is a gateway as are other things, right? But that brings me to a point that I keep not understanding. Why do threat modeling tools insist in labeling things with STRIDE?

**Matt Coles (12:19)**: Because it's a categorization system.

**Izar Tarandach (12:21)**: But again, you already have the threat. Why is it so important now?

**Matt Coles (12:25)**: Because it's recognizable and it's understandable to those who are gonna see reports.

**Izar Tarandach (12:29)**: But is it actionable or is it just one more field in the report that I'm looking at and think, oh nice, this is spoof. Yeah, I know it's a spoof, but the threat is saying this thing spoofs this thing.

**Chris Romeo (12:40)**: I agree with you. The STRIDE is a list of categories of threats that stand on their own. They don't define anything else. Like the way we approach the Devicis, like STRIDE is a set of threats that exist in the codex. But we also have threats from lots of other categories. I don't go through and tag things with stride pointers because I will disagree with you.

**Matt Coles (13:06)**: I will, we can agree to disagree.

**Chris Romeo (13:08)**: No, no, no, you gotta make, hold on, you haven't said why you disagree.

**Matt Coles (13:10)**: Go ahead. Well, because there's a whole range of threats that constitute spoofing or tampering, right? They are themselves categories. If you look at the early implementation of the Microsoft Threat Hunting tool, Right? They didn't have one threat that said spoofing. They had a bunch of threats that were under the spoofing category.

**Chris Romeo (13:28)**: But that constrains you too much today in the modern world where we have literally thousands of possible threats.

**Matt Coles (13:35)**: And by the way—

**Izar Tarandach (13:36)**: but imagine—

**Matt Coles (13:36)**: and by the way, threats don't have to be singularly categorized, meaning a single threat may not be one STRIDE category. There may be multiple STRIDE categories baked into a single threat.

**Chris Romeo (13:47)**: Yeah, but then you're using STRIDE too much as like the end-all and be-all.

**Izar Tarandach (13:51)**: No. Wait, wait, wait, wait, wait, wait, wait, wait, wait.

**Matt Coles (13:52)**: How did I say that? Well, I think you're putting words in my mouth here.

**Chris Romeo (13:57)**: Well, of course I am. That's how I work.

**Izar Tarandach (14:00)**: Let me invite you to look at this in a bit of a different light. If you look at the CWEs and you start from the root and you go down, things at the end of the day, when you identify threats, they get much more useful when you reach the final leaves than when you play in the middle.

**Chris Romeo (14:19)**: Sure.

**Izar Tarandach (14:20)**: STRIDE to me is a middle, is equivalent to a middle layer in the CWE. It's that generic thing.

**Chris Romeo (14:27)**: It's a class, yeah.

**Izar Tarandach (14:27)**: All the things that come under this are in this category, right?

**Matt Coles (14:31)**: Agreed.

**Izar Tarandach (14:32)**: So if I had tools pointing me to specific CWEs, okay, let me walk back from that back a second. I recognize that there is an educational value to pointing at a certain threat and saying this falls under this category of STRIDE. Because in the future, when the person is doing their own analysis, they are able to remember that and say, oh, wait, this new thing that I found is similar to that old thing that was found, and that was under spoofing. So this is another instance of spoofing, right? So there's an educational element there. But in terms of practical sense of making sense of the weakness that I have in hand, going as low in the CWE scale, not, not, not using the tree as a categorization, but scale of, of, of detail. I think it's still more useful than stopping in the middle at the stride level of categorization.

**Matt Coles (15:29)**: Agreed. Right. We're not talking about stopping at the middle. We're talk using it as, as a reference point.

**Chris Romeo (15:35)**: So do we have, so Matt, let me ask you this then. Do I have to have a stride category on every threat?

**Matt Coles (15:40)**: No. And in fact, I, I think you won't.

**Chris Romeo (15:43)**: Yes.

**Matt Coles (15:43)**: Right? So first off, if you have a privacy threat, you're not going to have a strike threat category, right? So not everything is going to map.

**Chris Romeo (15:49)**: Do you mandate a Linden categorization for privacy threats?

**Matt Coles (15:56)**: You're putting a word there that is— Kind of interesting.

**Izar Tarandach (15:59)**: Mandate. We don't do mandate.

**Matt Coles (16:01)**: We don't do mandate. So when—

**Chris Romeo (16:03)**: I mean, should you? Okay, so let me rephrase. Your Honor, I hear. Let me rephrase the question. Would you use the Linden categories similar to how you're describing using Stride as a categorization system? So if you had a privacy threat, you would pull through and say you should use the Linden categorization?

**Matt Coles (16:24)**: Probably highly recommended, yeah. I mean, as far as other privacy threat modeling goes, Linden is the reference point, right? Similarly, you know, if you had, so similarly, if you had, um, I guess, so here's where it gets interesting. You could use other things in place of stride.

**Izar Tarandach (16:44)**: Yes.

**Matt Coles (16:45)**: That are also similar reference points that are that similar middle layer of the, that we were talking about. What else?

**Chris Romeo (16:50)**: Give me another example.

**Matt Coles (16:51)**: So include, sorry.

**Izar Tarandach (16:54)**: Cool.

**Chris Romeo (16:55)**: What an intro. Wait, wait, wait. It's your time now.

**Matt Coles (16:58)**: Includes no dirt. Or was it SPARRA? But there's other acronym. It's— everyone's following the acronym base, but it's basically a set of principles.

**Chris Romeo (17:09)**: Nothing generic though. There's nothing. Those are all things that were very threat modeling specific, like NoDIRT was, uh—

**Izar Tarandach (17:14)**: Principles.

**Matt Coles (17:15)**: Well, you could go, yeah, you could go back to design principles from like NIST 800-160 Volume 1, or you could go to CWE or KPAC. I mean, not KPAC, because KPAC is really attack patterns and And you have the MITRE ATT&CK framework, which are ATT&CK patterns, but CWE, CWE class, uh, class, weakness classes is another good, another good reference point as if there was already—

**Izar Tarandach (17:41)**: but wait, I, I want to bring out something very, very important that Matt just said, apart from the other very important stuff that he keeps saying. There are other things. I think that. Something that we see recurring at this phase of the threat modeling community is dogma. There's a lot of dogma out there. You do stuff this way. This is the way that you do stuff. Now, I don't know if it comes from me being lazy. I don't know if it comes from me being nice. I don't know if it comes from me having seen a lot of stuff out there, but I don't care what you use. I care about your results. If you are in the point of your journey where stride gives you the best results, then use stride. If you are in a stage of your journey where I'm sorry for you, but cooking spaghetti does the best for you, go and cook spaghetti. You know?

**Matt Coles (18:39)**: Well, and so what if I don't like spaghetti?

**Chris Romeo (18:41)**: Again, I don't like spaghetti. Okay.

**Matt Coles (18:43)**: Well, then your journal, look like diet.

**Izar Tarandach (18:46)**: No, we don't like the dogmatic approach to there is only one way of eating and it's only spaghetti and it can only be cooked this certain way and everything else is that. That's what we don't like.

**Matt Coles (18:59)**: You use a giant fork and spoon and you're— Yeah.

**Chris Romeo (19:02)**: I want to, I just want to reiterate, I want to, what you said there was really important that I heard Cisco's previous CEO, John Chambers, used to say this all the time. Never confuse hard work with results.

**Izar Tarandach (19:14)**: Where do you think you heard that first?

**Chris Romeo (19:16)**: I probably heard it from— I didn't know that. I didn't know you knew him.

**Izar Tarandach (19:19)**: Nope, nope, nope. Wow.

**Chris Romeo (19:20)**: But that's what you're saying though, is like, it's— and we could just, we could change some words and say, never allow your threat modeling approach to, you know, never confuse that with results. So if you're getting results, that's the end of the day, that's making the product more secure and more private.

**Matt Coles (19:39)**: I think there's a threat modeling manifesto principle or value about that, if I recall.

**Chris Romeo (19:45)**: Sekhna?

**Matt Coles (19:47)**: So, um, so one, I, oh my gosh. Um, yes. Gosh, gosh, gosh, gosh, begosh. Um, I was going to say something kind of important too. Oh, uh, I wanted to counter, I wanted to counter your, just your thing about you should start with Stride because it's easy. Um, the reason why we have fret libraries is because Stride is not easy. If you take it at an extreme, right? So understanding what a spoofing threat is versus what's an implementation of a spoofing, or what's a, what's an actual threat that is under the category of spoofing. A lot of people start with STRIDE, and that's, I think, where a lot of people get lost unless they have somebody with security knowledge and experience on their team who's able to do that translation, which is why we have threat libraries.

**Chris Romeo (20:36)**: You're describing threat modeling in a vacuum. Which I don't recommend in the early days for people.

**Matt Coles (20:41)**: I'm not suggesting that at all, but that's why we have threat libraries, is so that somebody can take it and do it.

**Chris Romeo (20:44)**: I agree, I like threat libraries, I think they're powerful. I also like people to understand how to threat model by hand, if possible. It's like doing mathematics, right? Like, I'm not a math person, I am terrible at math, but there's always something about when you understand how to do the problem versus how to get the answer, it just changes your perspective on the thing and allows you to build other things on top of that thing because you got that concept, right? And so that's the only caveat for threat libraries. Yes, they're powerful, but I don't want to be in a mindless world where people are just like, I ran the tool, I got these 3 results, I created the tickets and I moved on. I want them to understand because, listen, I build a threat modeling platform and brainstorming has still got to be a part of what we do here. I can't create a threat library that takes Isar and Matt's experience in the different jobs you've had and meld them together into something that will spit out creative new threats as people have ever thought of. I need the human beings to drive that based on their experience. And so that's my only caveat there is I like, I want to make sure people know how to do this versus just knowing how to access a threat library.

**Izar Tarandach (21:55)**: So that's the thing, threat libraries and What was the other thing? The other thing that we were supposed to— Forget about it. Threat libraries. So my problem with threat libraries is that they lead to two things. First of all, threat modeling by looking at the rearview mirror. Like that's been my analogy for a long time ever since I first encountered threat libraries. You're driving a car and you look at the rearview mirror at the things that already passed. Eventually you are going to hit something new going forward, but you are so focused on that thing that you won't see it coming. You won't recognize that it hits and there's probably going to be a horrible accident. So while I understand their value and I see their value, I think that they are by definition limiting and in double, triple, quadruple airports dangerous for people who are just going on that on-ramp to assume as their methodology or their way to learn. And the other thing that I think they lead to, and, and this is something that I, I have talked with, uh, Brooke extensively about, is, uh, cargo cult mentality. At some point, the threat library becomes a threat checklist. And then moving from there, you start just checking those things because it's the things that we always check because it's the things that when one person checks way past in the past, they got results. So if we keep doing those things the way that that person did, we might get results.

**Matt Coles (23:34)**: Mm-hmm.

**Chris Romeo (23:35)**: And, and you call it, hold on, just what you, what, what were those, the two words you used to call this?

**Izar Tarandach (23:40)**: Cargo cult.

**Chris Romeo (23:41)**: Cargo cult.

**Izar Tarandach (23:42)**: That comes from a thing that happened at the end of World War II in the Pacific. They had the US-built airstrips in small islands that had some native population. And the native population after the war, they developed the habit of building runways, like sea miles of runways, because they associated that with sorium. It's going to sound very condescending, which the big bird coming from the sky and bringing food and things. So they believe that if they only build the runway, the big bird will come back. And that's how tough things were.

**Matt Coles (24:26)**: Yeah. And we should just highlight that, of course, today is Veterans Day here in the US. Oh yeah. Uh, and thank you all. So, um, you know, so what you highlighted though is, is really important and why Stride actually still has value. So if you use a threat library to identify threats and you identify the threats that are already encoded in the threat library, as soon as you incur, as soon as you identify the opportunity for something new, right? Assuming you're not looking at, you know, blinders on looking at only what's in the threat library and, and you have the ability to find or where you do come across something like, hey, this doesn't fit anything in our list, but it's still a threat we want to consider. Well, how are we going to consider that? Well, you may take it up a notch to that parent class, right? AKA the STRIDE classification. Hey, this is like a spoofing threat. It's not in our threat library. It's not a listed threat as a spoofing threat in our threat library, but we've now identified something new. Well, how do we describe it? Well, we might describe it by mapping it to a stride category. And now I have a way, a basis, you have a, now have a basis for describing it in a way and looking for its properties to be able to then put it into your threat library for later, right? So that you can now start building on your threat library.

**Chris Romeo (25:47)**: You guys ready for some controversy here? Absolutely.

**Matt Coles (25:49)**: What is, what would today be without controversy?

**Chris Romeo (25:52)**: This is, I'm going to, wait, I need another coffee. Yes. Take it. We're going to, we'll be back after this, these short messages for Yezar to get an espresso or two. Is the cat— are the categories that are represented in Stride still relevant today like they were? I just, this has got me thinking as we've been talking, I went on this kind of thought experiment. Spoofing and tampering both. The counter to spoofing and tampering is encryption, maybe some input validation. But normally we think of encryption as being the counter to those things. Like, if you encrypt or if you use multifactor authentication from a spoofing perspective, how prevalent is spoofing anymore though?

**Matt Coles (26:38)**: Well, you're asking the wrong question. It is not complete, but it is still relevant. Spoofing still exists. Just be— first off, if you implement multifactor authentication, you do not eliminate spoofer.

**Chris Romeo (26:50)**: Of course, but it's a great step in the right direction though. Yeah, absolutely it is.

**Matt Coles (26:55)**: Uh, Matlocky. And if you implement encryption, whether on the wire or at rest, you're not going to solve all tampering problems, right? Or all information discovery problems.

**Chris Romeo (27:04)**: Give me an example of a tamper. How are you going to tamper? What are you going to tamper with that's something that's encrypted?

**Matt Coles (27:12)**: Well, what if I tamper with the encryption key?

**Izar Tarandach (27:15)**: I can tamper and it won't unencrypt, but it will still break the way that the thing's supposed to work because they did not consider the fact that something can fail to be decrypted.

**Chris Romeo (27:25)**: Yeah, well, my point was—

**Izar Tarandach (27:28)**: Before that—

**Matt Coles (27:28)**: Well, then you may actually— sorry, you may argue that's a denial of service threat, but we could talk about that later.

**Izar Tarandach (27:35)**: But the fact that you can tamper with it, like that you have access to tamper with it. But anyway, one important thing to point out is that while I agree with you and you've got definitely a thing going on there, I think that it's perhaps it's just my the way that I approach Stripe, but I think that the categories, they apply at different layers that may go up and down the scale of, yeah, sure, this particular spoofing is fixed by this particular kind of authentication. But if you take things up many levels, you even get to business case of the thing. So all of a sudden, the threats are different. They are higher level. They are fixable perhaps by processes or something like that that do not involve some form of digital authentication or the always evolving world of certificates and whatnot. But I think that's the concept of the weakness is important, especially for those people who come from a background of no security. The simple fact that you are able to get those 6 things. Yeah, thanks. And explain to people what these 6 things are. You are already giving them so much of a leg up in terms of things to look out for at different levels, at all levels.

**Chris Romeo (29:00)**: But those are not as prevalent as, or as relevant, I say even relevant, you can say they're prevalent. They're not as relevant as they were. So I guess, should we go back to the drawing board and should we create a new Stride for 2024? Because listen, I mean, Lauren, I've talked to Lauren Kornfelder about this. Everybody thinks Adam is the creator of Stride. Adam didn't create Stride. It was Lauren and another guy at Microsoft. I can't remember. I always forget who the other guy's name was. I'm sorry. But this is, they did this in the '90s, right? Or maybe the early 2000s. I mean, A lot has changed in technology. So I guess the question I pose to you is, should we go back to the drawing board? We know that the vehicle of STRIDE is powerful because it provides an on-ramp to threat modeling. Is it time to refactor STRIDE?

**Izar Tarandach (29:48)**: Wait, wait, wait, two things. That paper, and now the name skips me, that paper from the '70s, '72, with the fundamentals of computer security.

**Chris Romeo (29:58)**: Schrader and Salzer. Salzer and Schroeder.

**Izar Tarandach (30:00)**: Salzer and Schroeder. That thing was written when Unix was like coming up at Bell Labs. Two weeks old, definitely. And it's still relevant. But I had a point about, oh yeah, yeah, yeah. So what I'm hearing you say, please correct me if I'm wrong, is that the catalog of things that some people decided to call The things we have to do to achieve security by design plug very nicely into the STRIDE buckets and therefore have fixed those categories of threats. So now we should look at a different evolution of STRIDE in order to make people look at different tools that would fix those new buckets that we have identified now.

**Chris Romeo (30:52)**: That's not how I got there. But what I'm just, listen, I'm not even, I haven't made up my mind. I haven't made up my mind yet as to whether we need to— I don't know if we need to refactor this. I'm not, I'm not saying we have to. I just think, I think it needs to be extended.

**Matt Coles (31:06)**: I think— wait, you're, you're, I don't, I don't agree with you that, that we don't have spoofing just because we can solve spoofing.

**Chris Romeo (31:14)**: No, I said, is it, I said it wasn't relevant. So you're saying—

**Matt Coles (31:16)**: so that's what you're saying is it's not relevant because it's no longer a problem, but it's still a thing. And so, and, and if you—

**Chris Romeo (31:24)**: Would you agree it's a lot less prevalent?

**Matt Coles (31:27)**: It doesn't matter about prevalence.

**Chris Romeo (31:29)**: But why would you want to teach— this is— we're talking about a foundational piece we're going to use to teach people how to get started with this. If we give them something— hold on— if we give them something that returns no value from their perspective, then they're going to go, why the heck is Matt making me do this?

**Matt Coles (31:44)**: Because you're making an assumption. You're making an assumption that technology is stagnant. Once you fix a problem, it never returns.

**Izar Tarandach (31:51)**: How do I know that right now I'm talking to Chris and not to a spoofed AI-generated avatar that's trying to convince me that spoofing is not a problem anymore so that in 5 years they can come and exploit all the new spoofable stuff?

**Chris Romeo (32:04)**: These are the 3 laws of robotics from Isaac Asimov.

**Matt Coles (32:09)**: AI is not a robot. AI is not a robotic.

**Chris Romeo (32:12)**: I think Matt's a robot.

**Izar Tarandach (32:14)**: Matt's a robot.

**Matt Coles (32:15)**: I'm a lawyer.

**Chris Romeo (32:16)**: That's what a robot would say.

**Izar Tarandach (32:17)**: I'm not a lawyer.

**Matt Coles (32:18)**: I just, I just watched, I just saw the episode about, uh, on The Simpsons when Mr. Burns replaces all the workers with robots. If you haven't seen it, it's hilarious. But it dives into this exactly.

**Izar Tarandach (32:31)**: But seriously, I mean, yeah, that classic problem of spoofing that we solved with that classical solution that everybody should be doing and by God, not everybody is doing. Yeah, that one got solved. But you know, we keep bringing in new people and here I go on the soapbox again. We keep not teaching people security fundamentals from the get-go. So this thing that has served us so well to teach a whole one, two, three generations of people right now, tech people, not born people. Should we deep-six it just because we sort of have a solution that's not enforced, that's not taught, that's not required, and that's not universal. Or should we just keep it open?

**Chris Romeo (33:20)**: Yeah, I'm not saying dump it. So I, I, I still stand behind STRIDE as a vehicle. The question I'm asking is, should we refresh it based on current— I mean, it's been 25 years since that list was created. It's probably a lot of change in technology. We went from, we went from mainframe to personal computers back to the cloud.

**Matt Coles (33:39)**: But, but by the way, mainframe, personal mainframes and personal computers still exist, right? And now you have hardware and of course software.

**Chris Romeo (33:46)**: As the prevalence, as the prevalence might continue.

**Matt Coles (33:50)**: Well, sure, but you don't want to create a thing that's only good for, you know, you don't want to restrict what you're looking for. Well, unless you do. I mean, if you're looking at medical devices, you probably don't need to look at things that would only affect, you know, transportation systems.

**Chris Romeo (34:05)**: So how could we, how could we do that? We need an experiment. To test the relevance of, of Strag categories today.

**Matt Coles (34:13)**: Oh no, he's doing it.

**Chris Romeo (34:17)**: Please don't ask. He's our tech. He's, he's actually literally sending an email to Brook Schoenfeld.

**Matt Coles (34:24)**: No, I think he's asking ChatGPT.

**Izar Tarandach (34:26)**: To his friend Claude. To his friend Claude.

**Chris Romeo (34:31)**: All right, now everybody's on the edge of their seats trying to wait for the answer, but you keep typing.

**Matt Coles (34:37)**: And oh, and oh, by the way, and oh, by the way, even if it's not, you're not teaching a human, you still have to describe these things to AI so that they can recognize it. Sure.

**Izar Tarandach (34:48)**: Oh boy.

**Chris Romeo (34:50)**: Oh, enlighten us.

**Izar Tarandach (34:52)**: Here's the question. How would you refresh the STRIDE categories to be more relevant to today's security landscape? Everybody agrees with the current question? Sure.

**Matt Coles (35:00)**: Sure.

**Izar Tarandach (35:01)**: I apologize, but I do not have the capability to directly update or modify the STRIDE security model.

**Chris Romeo (35:06)**: I think that Claude is afraid of Adam.

**Izar Tarandach (35:08)**: As an AI assistant, I do not have the authority or access to change established security frameworks.

**Chris Romeo (35:15)**: I think this is a problem with prompts.

**Matt Coles (35:18)**: Wait, wait, wait, wait.

**Izar Tarandach (35:20)**: However, however, I can provide some general suggestions to how the STRIDE categories could potentially be refreshed to stay more relevant in the current security landscape. One, expand the spoofing category to account for emerging threats like deepfakes, credential stuffing, and other identified-based attacks. Thank you. Thank you very much.

**Matt Coles (35:39)**: So wait, wait on. Stop right there. So keep spoofing and expand on what within that category?

**Izar Tarandach (35:46)**: It's saying it wants to expand everything. Enhance the tampering category to address supply chain vulnerabilities, firmware/hardware manipulation, and attacks on IoT industrial control systems. This thing has been listening to Matt. Incorporate repudiation concerns around blockchain, cryptocurrencies, and the challenges of non-repudiation in distributed systems. Ta-da-da! Explore expanding information disclosure to cover data breaches, sensitive data exposure, and privacy violations in the era of big data and cloud computing.

**Chris Romeo (36:19)**: No, now you're just saying— Okay, that's just a bunch of drivel. It's just a bunch of like buzzwords.

**Matt Coles (36:23)**: 2020 wants their computing technology back.

**Chris Romeo (36:26)**: All right, I'm running, I'm running the question through ChatGPT 01 preview, which is advanced reasoning.

**Matt Coles (36:32)**: So we're on the ball here. Okay.

**Chris Romeo (36:36)**: It literally says enhancing Stride right now. That's, that's the feedback and expanding threat categories. So get ready. There's going to be a big reveal here in about 20 minutes. So we get stunned.

**Matt Coles (36:47)**: Yeah, this, this does not come without a cost. And by the way, and by the way, Let's talk about, let's talk about, uh, denial of service when you don't have enough power or compute to be able to run and read the line.

**Izar Tarandach (36:59)**: No, that's not.

**Matt Coles (37:00)**: That's not the future.

**Izar Tarandach (37:01)**: No, that's not.

**Chris Romeo (37:02)**: Stop denying his service.

**Izar Tarandach (37:03)**: No, that's not.

**Chris Romeo (37:04)**: No, I don't.

**Izar Tarandach (37:05)**: Okay.

**Chris Romeo (37:06)**: This actually, this actually is interesting. So the first thing that ChatGPT says is incorporate privacy threats. Stride-P. Uh-huh. Interesting. Like it would be Stripes. Yeah.

**Izar Tarandach (37:20)**: Where have I learned that?

**Chris Romeo (37:22)**: Address supply chain risks, include AI and machine learning threats, cloud and container security, zero trust architect. Now it's just going off the rails.

**Matt Coles (37:31)**: Yeah. So enhancing STRIDE to include privacy and safety would actually, would be a good enhancement. Make it Stripes.

**Chris Romeo (37:39)**: Yeah. But I like address supply chain risks doesn't work. Like you, that, that has to fit. Supply chain risk has to be in another bucket. That says expand the tampering category. Maybe that's what it is. You know what? Here's an idea. Maybe what we need is just a modern set of examples.

**Matt Coles (37:54)**: We need an exploded, we need to explode out the classes of things, right?

**Chris Romeo (37:59)**: I mean, that's what ChatGPT just said. Hold on. It just said enhanced tampering definition. Expand the tampering category to explicitly include supply chain attacks where adversaries compromise software components before they're integrated. That is tampering though, right?

**Izar Tarandach (38:13)**: That is tampering. But then you don't have a categorization. You have a catalog and then you try to catalog everything under the sun. Well, no, it's a—

**Chris Romeo (38:20)**: No, no, no, no, no. This is just a couple of examples to prove that stride is relevant today. That's the problem is everybody's saying stride is dead and nobody's fighting back and saying— Everybody's saying, well, no, it's not. So that's a terrible argument, right?

**Izar Tarandach (38:34)**: Like, wait, wait, wait, wait, wait, wait, wait, wait, wait. I lost you on everybody saying that stride is dead.

**Chris Romeo (38:38)**: I'm just— okay. No, I mean, so, okay, people are saying— my point is, though, that we could, we could put together a pretty quick list of like 1 or 2 or 3 examples of more modern uses of the Stride category, like supply chain compromise in the tampering category.

**Izar Tarandach (38:55)**: All—

**Chris Romeo (38:56)**: now I'm back on board. I'm back on Team Stride now. As soon as I saw that, I'm like, yes, that makes sense. It's relevant. It is. Those things are happening.

**Matt Coles (39:05)**: It needs work. Yes. But it's still value. It still has value. And then it's, and then, and then pulling it back, right? We still haven't solved the problem of threat modeling is dead. Threat modeling is a process.

**Izar Tarandach (39:18)**: Oh.

**Matt Coles (39:19)**: Right? And, and we don't, we don't have time for it today, but maybe that's our next episode is, so if STRIDE is a category of threats, how do we get there? How do we identify threats? And that's a process. Right? We know the 4-question framework. We know CASTA is there. We know that there's other things that might be, might be present as methodologies where STRIDE can be applied. But STRIDE itself is not a methodology for threats.

**Chris Romeo (39:46)**: I think we might need to gather our group and quickly knock out a— Assemble the Avengers. Assemble the Avengers. That's the best I can say.

**Matt Coles (39:56)**: Threat modeling Avengers. Threat modeling assembles.

**Chris Romeo (40:00)**: I hear the music playing right now in my head from the Avengers movies. Yes. Who's the Incredible Hulk in that situation though? Don't even answer that.

**Izar Tarandach (40:08)**: Um, you really don't know how to see me pissed off.

**Chris Romeo (40:11)**: Yeah, that's, that's my secret. That's my secret, Izar.

**Matt Coles (40:14)**: I'm always angry.

**Chris Romeo (40:15)**: All right, well, that's it. That's— we had enough fun for one day. I think we, we had some, some good debates. We had some good just good ideas unlocked there. I think Stride is alive and we just need to, we need some proof. We need to prove it. We need to provide some examples to prove that people can't just say this is dead. Well then, so supply chain attacks don't matter to you? We gotta do a little bit more work to be able to line this up.

**Izar Tarandach (40:46)**: The proof is in the usefulness. As long as it's useful for somebody out there, it's not dead.

**Chris Romeo (40:51)**: That's true.

**Izar Tarandach (40:51)**: It's almost a Peter Pan thing. If you put it in stride.

**Matt Coles (40:54)**: All models, all models are wrong. Some are useful.

**Izar Tarandach (40:57)**: Exactly.

**Chris Romeo (40:58)**: And with that, thanks for listening to the Security Table.
