Please create an account to participate in the Slashdot moderation system

 



Forgot your password?
typodupeerror
×
AI Security

Bruce Schneier Reminds LLM Engineers About the Risks of Prompt Injection Vulnerabilities (schneier.com) 40

Security professional Bruce Schneier argues that large language models have the same vulnerability as phones in the 1970s exploited by John Draper.

"Data and control used the same channel," Schneier writes in Communications of the ACM. "That is, the commands that told the phone switch what to do were sent along the same path as voices." Other forms of prompt injection involve the LLM receiving malicious instructions in its training data. Another example hides secret commands in Web pages. Any LLM application that processes emails or Web pages is vulnerable. Attackers can embed malicious commands in images and videos, so any system that processes those is vulnerable. Any LLM application that interacts with untrusted users — think of a chatbot embedded in a website — will be vulnerable to attack. It's hard to think of an LLM application that isn't vulnerable in some way.

Individual attacks are easy to prevent once discovered and publicized, but there are an infinite number of them and no way to block them as a class. The real problem here is the same one that plagued the pre-SS7 phone network: the commingling of data and commands. As long as the data — whether it be training data, text prompts, or other input into the LLM — is mixed up with the commands that tell the LLM what to do, the system will be vulnerable. But unlike the phone system, we can't separate an LLM's data from its commands. One of the enormously powerful features of an LLM is that the data affects the code. We want the system to modify its operation when it gets new training data. We want it to change the way it works based on the commands we give it. The fact that LLMs self-modify based on their input data is a feature, not a bug. And it's the very thing that enables prompt injection.

Like the old phone system, defenses are likely to be piecemeal. We're getting better at creating LLMs that are resistant to these attacks. We're building systems that clean up inputs, both by recognizing known prompt-injection attacks and training other LLMs to try to recognize what those attacks look like. (Although now you have to secure that other LLM from prompt-injection attacks.) In some cases, we can use access-control mechanisms and other Internet security systems to limit who can access the LLM and what the LLM can do. This will limit how much we can trust them. Can you ever trust an LLM email assistant if it can be tricked into doing something it shouldn't do? Can you ever trust a generative-AI traffic-detection video system if someone can hold up a carefully worded sign and convince it to not notice a particular license plate — and then forget that it ever saw the sign...?

Someday, some AI researcher will figure out how to separate the data and control paths. Until then, though, we're going to have to think carefully about using LLMs in potentially adversarial situations...like, say, on the Internet.

Schneier urges engineers to balance the risks of generative AI with the powers it brings. "Using them for everything is easier than taking the time to figure out what sort of specialized AI is optimized for the task.

"But generative AI comes with a lot of security baggage — in the form of prompt-injection attacks and other security risks. We need to take a more nuanced view of AI systems, their uses, their own particular risks, and their costs vs. benefits."
This discussion has been archived. No new comments can be posted.

Bruce Schneier Reminds LLM Engineers About the Risks of Prompt Injection Vulnerabilities

Comments Filter:
  • "we can't separate an LLM's data from its commands"

    Seriously? Who thought having a single stream for commands and data was a good idea never mind in 2024 but ever FFS?

    If I type stuff into a word processor I don't expect to suddenly go off and try and delete my filesystem if I enter "rm -rf /" similar so why would an LLM look for commands in its runtime input data? Am I missing something here?

    • by znrt ( 2424692 ) on Saturday May 18, 2024 @11:19AM (#64481309)

      Seriously? Who thought having a single stream for commands and data was a good idea never mind in 2024 but ever FFS?

      errr ... bruce schneier stating the obvious for some reason? half of the point of llm's is parsing commands, good luck designing around that.

      the real problem here is that beyond all the fanfare and excitement we don't truly understand how they work, and it seems we won't for a good while. spoiler: bruce schneier doesn't either.

      • by evanh ( 627108 )

        But he has grokked the weakness of placing a LLM public facing. There's certainly plenty of evidence to back his claim. And not just cunning security bypasses. Also stupidity of output, that some will blindly follow.

        And to flip that - If LLMs are so easily messed up then how could they be relied upon when not public facing. Then we don't get to see the source of the mess unless the private entity works it out and then fesses up.

    • "we can't separate an LLM's data from its commands"

      Seriously? Who thought having a single stream for commands and data was a good idea

      The same people who thought making the Presentation Layer a de facto extension of the Application Layer was smart engineering.... So now most platform vulnerabilities are heap/presentation layer/prompt attacks now.....

    • by WaffleMonster ( 969671 ) on Saturday May 18, 2024 @12:45PM (#64481433)

      "we can't separate an LLM's data from its commands"
      Seriously? Who thought having a single stream for commands and data was a good idea never mind in 2024 but ever FFS?

      For LLMs it's all there is. Humans are no different. We don't have dedicated command streams either, we have to discern context and disambiguate and decide what to do from our understanding of the environment. The massive success of phishing attacks owning millions is a testament to the imperfect nature of flawed systems meet flawed human operators.

      If I type stuff into a word processor I don't expect to suddenly go off and try and delete my filesystem if I enter "rm -rf /" similar so why would an LLM look for commands in its runtime input data? Am I missing something here?

      LLMs are kind of like people in a way that they are not very good at discerning complicated or confusing context from a wall of text and often times they are far worse.

      If you had a bunch of quotes of people quoting other people quoting things a person would quickly become confused and lose track of who is quoting who. LLMs are at least as bad.

      With computers we have fancy UIs and can always see application windows and most of us can discern context between text on an arbitrary website and our boss calling us up to give us more tasks. Imagine if instead of all that you only had a green screen with a stream of text. While reading the website you lost track of where you are because the site contains data that looks like the website ended a while ago and your boss telling you what to do started. A person could easily be confused by that, their attention may have slipped not noticing the special control signal that is supposed to alert them to context changes.

      LLMs are no different and often much worse. The best you can do is a solution to make context far more obvious to the LLM with the equivalent of that fancy UI that always makes it unambiguously and persistently clear which window is the website and which is the boss on the telephone. But still if injection is an issue people are probably misusing LLMs for something they shouldn't be relying on them for in the first place.

      • LLMs are just software, not magic. There can be one channel for user input and another for system commands.

        • by EvilSS ( 557649 )

          LLMs are just software, not magic. There can be one channel for user input and another for system commands.

          Well hey look, problem solved! All the current engineers couldn't do it but Viol8 apparently has it licked! Can't wait to see who hires you to implement it.

          • You don't even need separate input streams for this. You can do what ancient, obsolete line editors such as vi did: you start out in command mode, so that the program treats everything as commands; then, if you need to, you switch to data mode so that anything you input is considered as data until you enter something special that takes you back to command mode. And, when you're in data mode, nothing you enter except that special signal is, or can be taken as a command by the program.
            • Yeah, that must be one of the reasons why vim is the leading word processor worldwide.

            • by EvilSS ( 557649 )
              I think part of the problem is the summary and Bruce calling out a "data channel vs command channel". That makes it sound like there is even the possibility of such a thing with LLMs. There are not. Every interaction with a model is a command. That's how they work. You ask the model to do something, and it does it. The problem is preventing the model from doing something you don't want it to do with normal user input. You can filter input, in some instances like training you can disable prompting, you can u
          • Obviously this was meant to be sarcasm but there's a real cause to call their competence into question over this. To be honest I've been looking for any proof in the news that these jackasses even invented this themselves rather than stealing or buying it in binary-blob-only format under the table from Russians or something like that, and there's none.

        • by gweihir ( 88907 )

          Oh? And how do you deal with interaction created state? Because for an LLM, that is "system commands", and it is needed to make them a bit more useful. A purely static LLM is so utterly dumb, it cannot do anything. In particular, it is impossible to customize for a regular user.

      • LLMs are kind of like people in a way that they are not very good at discerning complicated or confusing context from a wall of text and often times they are far worse.

        A friend of mine said the same thing... If LLMs are a reflection of how the human brain works, then they're susceptible to the same attacks that we see nowadays in society: allow it to learn the wrong things, and it will spill out the wrong answers. Train it on conspiracy theories and it will spew out conspiracy theories.

        The attack surface is humongous, and it will only get worse as training happens iteratively on fake news as the years progress. Next year there will be a lot more content created by LLMs, a

    • Yes, you are missing something, human conversation (which "LLM" are supposed to emulate) does precisely that, it mixes control with data and leaves it to the free agents on both sides of the conversation to decide for themselves how to implement the incoming stream.

      So,

      a) it is inevitable due to the nature of the thing LLM are emulating :) and
      b) how harmful it gets depends on the "intelligence" of the agent

      You already see how it is going to work out, don't you?

  • The same data-channels - my 5 (or more?) senses - tell me if my food smells like Grandma's famous apple pie (stored as information) or is putrid (arguably an "instinctive command" to avoid eating the item, at least according to some theories).

    Sometimes that causes problems, like missing out on some supposedly-good-tasting but horrible-smelling cheeses that I haven't had the courage to try.

    By the way, my example is open to quibbling, but the general principle stands: There are times when people can be foole

    • by gweihir ( 88907 )

      Indeed, it does. And then look at how easy most people are to scam or to manipulate. Incidentally, the input generally does not need to be that well-crafted for most people. Just look at politics and observe what Big Lies people are ready to eat up. Effective propaganda is always designed and targeted at those with the weakest minds. Written down and implemented a while back by a guy called Hitler. That approach still works nicely today. No, I have not read "Mein Kampf". But I think maybe I should. The com

  • Someday ... they'll be safe. No. We're training them to be just like us, as smart as us. So someday they'll fall for e-mail scams, phishing attacks, and believe all the crap from lying politicians, just like we do. But they'll fall for these at electronic speeds, and probably get woke too. God help us if that day ever comes.
  • Regular software vulnerabilities are kid stuff compare to the attack surface present here. We do not even really understand the models. For conventional attacks, regular program semantics is used or a small number of mostly understood side-channels. These may get used or combined in surprising ways, but at least we understand the base mechanisms pretty well. With LLMs? We have no clue what is possible.

    I like the analogy to classical telefone signalling. It is not perfect, but the best one I have seen so far

    • by narcc ( 412956 )

      With LLMs? We have no clue what is possible.

      That's simply not true. The limits are very well understood, contrary to what the marketers would have you believe.

      As for the attack surface, that should be clear as crystal for any given implementation. These things aren't magic. I don't know who Schneier thinks he's talking to, but if you're trying to impose strictures by fine-tuning an LLM, you don't need a warning, you need to be fired for gross incompetence.

      • by gweihir ( 88907 )

        Hahaha, no. The _limits_ of what intentional things an LLM can do are reasonably well understood. The limits of what an LLM can be tricked into doing are somewhat understood on the theoretical side, but on the practical ones they depend very strongly on the training data and on implementation details, like temporary state or persistent state depending on user and the interactions with it. Hence the concrete possibilities are _not_ understood at all for any of the LLMs currently deployed.

        You are thinking lik

        • by narcc ( 412956 )

          You're waving your hands an awful lot... As for the security issues, you've dramatically over-complicated the problem.

          Your mistake in reasoning, as far as security is concerned, is that you're assuming that the LLM can do more than would otherwise be possible given access to the same interfaces. Sticking an LLM between the user and those interfaces doesn't magically increase the attack surface. If anything, it narrows it as the range of possible inputs is unlikely to completely overlap with the range of

  • Schneier has apparently never heard of the VERY old saw, "Don't try to teach your grandmother to suck eggs." Yeah, now it would be great grandmother or great great grandmother who last "sucked eggs"; but, the idea stands, "Don't try to teach an expert what he or she already surely knows."

    {^_^}

Hokey religions and ancient weapons are no substitute for a good blaster at your side. - Han Solo

Working...