22 comments

  • rwmj 15 minutes ago
    > "At the time of publication, no robust mitigation for the broader vulnerability class is available"

    Isn't it obvious by now that it's never going to be possible to fix this kind of thing, at least until we stop mixing up instructions with data.

    • Marha01 11 minutes ago
      > until we stop mixing up instructions with data

      Is such a thing even possible with a generally intelligent system processing content with unlimited diversity?

      • TeMPOraL 9 minutes ago
        It's neither possible nor desired, and until that fact clicks for majority of computer people, we'll be running in circles and making a mess through futile attempts at solving the problem at the wrong end.
      • nolok 8 minutes ago
        I would wager the fact that it's not what your sentence says is why that is possible. The moment it gets actual "intelligence", it can figure out what's the question and what's the context; right now it's all just a magic jumbo mess.

        If any of this thing were "a generally intelligent system", the whole concept of "it has no idea what any of this is" would not be there.

    • yifanl 9 minutes ago
      We're back to Von Neumann architecture in the worst way possible.
  • simonw 1 hour ago
    > Malicious instructions hidden in an externally shared document could make Copilot alter drafted or edited documents in Word and propagate the attack to new documents.

    Oh no.

    • fg137 1 hour ago
      Mixing instructions and data is never a good idea.

      And I thought people understood that.

      • WJW 26 minutes ago
        Security minded programmers understand that. "People" as a whole have not even heard about mixing instructions and data, and certainly not the reasons why it is not a good idea.

        And AI chatbots are very much targeted at the second group, not the first.

        • TeMPOraL 7 minutes ago
          > "People" as a whole have not even heard about mixing instructions and data, and certainly not the reasons why it is not a good idea.

          Because it's not a concept in the real world. Physical reality has no such separation, and neither do human minds.

          Tell people you're discussing a board game or some sport, then they'll understand - other than bureaucracy (scary!) and school (traumatic!), that's the one kind of artificial system with rules affording for code/data separation that general population has most experience dealing with.

        • iamacyborg 13 minutes ago
          > And AI chatbots are very much targeted at the second group, not the first.

          I suppose this is why the AI labs are famously not releasing developer-oriented tools.

      • wongarsu 13 minutes ago
        People understand that. They just don't know how to implement that with LLMs

        In the GPT-2 era LLMs were just data. Instructions did not exist, and if you added them to your data they would not be followed. Then around 2022 we figured out how to patch in instruction following with a bit of fine tuning, leading to the current AI bubble. That's an ugly hack that leads to all these issues. But it's what this entire AI bubble is founded on. And nobody seems to have found a better way (or at least one that actually scales and doesn't make unreasonable sacrifices)

        • TeMPOraL 6 minutes ago
          Sure they would be. But for those old models, you'd have to prompt it in a framing of a screenplay or something.

          You're forgetting that LLMs just output a stream of tokens - the interpreter that acts on those is a piece of classical code, and sits outside of the model.

      • TeMPOraL 42 minutes ago
        Separation of instructions and data is artificial. Reality has no such separation. A general purpose system needs not to have them either; it's a design feature, not a bug.

        People get too hung up on this fundamentally wrong idea, and the space of security, instead of progressing, is just running in circles like a headless chicken, making a mess of everything.

        • jclulow 33 minutes ago
          Literally all of software is artificial? Being explicit and reasoned about how you choose to allow or deny a particular computation is, surely, at the heart of a lot of computer security?
          • TeMPOraL 16 minutes ago
            Code/data separation is at the heart of computer security in the same way slapstick comedy is at the heart of humor.

            There's an endless supply of people who think they know what is Code and what is Data, and they're always arguing with others who also think that, and neither realize that Code/Data classification is an opinion, a perspective. It doesn't hold in general.

            Having a separation like this makes sense for super narrow systems, where you can define the allowed and disallowed use cases, enforce the distinction (because it's not real - therefore you have to enforce it mechanistically within your system), and willing to accept that some useful operations will be denied by your system.

        • KolibriFly 28 minutes ago
          With that logic you could call SQL injections a natural feature of database management systems. If a general purpose system starts dropping tables or messing up numbers in a report just because that string was in the text it read, that system isnt worth a damn in the enterprise sector
          • TeMPOraL 10 minutes ago
            This is why I insist that anthropomorphising LLMs is not only not a mistake, it's a best source of high-level intuition for these systems.

            Long story short: on a systems diagram, LLM as a component isn't a substitute for a database engine or a data processing script. It's a substitute for a human operator.

            So ask yourself, if a human operator starts dropping tables or messing up numbers in a report, just because that string was in the text it read, would you call for humans, what would you do? Do you believe it's possible to perfectly train people to ignore the messages you'd wish (after the fact!) they'd ignored, while retaining their ability to competently act on every other message?

            Or would you instead design the deterministic parts of the systems to limit the blast radius of any single insider going rogue?

            Wisdom says to do the latter.

        • yoz-y 34 minutes ago
          Only in systems that need to be themselves super generalist. Which is almost never the case.
          • Marha01 10 minutes ago
            > Which is almost never the case.

            Well, the topic is about AI..

          • TeMPOraL 34 minutes ago
            LLMs are.
      • catlifeonmars 12 minutes ago
        People who use machines based on the von Neumann architecture?
      • dev_l1x_be 44 minutes ago
        There are so many better alternatives but it seems many people really like Word for some weird reason. The last time I cared I had to look up how to make a document starting the page numbering on the 2nd page. It turns out there are totally different ways between different versions of Word. shrug.jpg
      • bossyTeacher 56 minutes ago
        Isn't React, the most popular JS library, an example of that? Clearly people don't understand that
        • an0malous 53 minutes ago
          No it’s not an example of that. Do you store components in your component state?
          • cj 43 minutes ago
            He probably means JSX mixing HTML with Javascript...

            function Greeting({ name }) { return <h1>Hello, {name}</h1>; }

            • TeMPOraL 35 minutes ago
              You just did that in a HN comment, yet nothing happened :).

              Could it be that the whole idea is silly misunderstanding of fundamental tenets of reality in the first place?

    • veganmosfet 53 minutes ago
      Indeed - but some models are more robust than others. I tried to make Opus-5 execute hidden instructions embedded a picture using steganography. It's very hard to find a reliable payload.
    • fxwin 1 hour ago
      something something lethal trifecta
      • TeMPOraL 34 minutes ago
        And Santa Claus, and other fairy tales we tell small children before they're ready to understand how reality actually works.
        • sarchertech 18 minutes ago
          Are you just going to hop around every thread on this article and be snarky?
          • TeMPOraL 3 minutes ago
            Yeah, because "code/data" and "lethal trifecta" are my pet peeves this half-decade :). I don't like that we're still turning in circles as an industry, because majority seems to have a very flawed model on the reality of the problem.
      • baq 1 hour ago
        waiting for W^X reinvented, renamed and marketed for the Agentic Era (r)TM
        • Ragnarork 37 minutes ago
          Self-replicating Inference Guardails Hardening or SIGH
    • TeMPOraL 37 minutes ago
      Breaking just now:

      - Erroneous information left in plain sight in an externally shared document could make Copilot - or any other agentic system, including LLMs and protein-based intelligence, alter drafted or edited documents in Word (or any other program, or with pen and paper) and propagate the errors to new documents.

      In other news:

      - Many humans still believe in silly superstitions like flat Earth or that code and data are fundamentally distinct, or that control vs. data plane is anything more than a design opinion that doesn't apply to the universe in general.

  • averagjoe 40 minutes ago
    I'm a programmer and a web-based AI user, but I don't want AI running on my local machine in any form. I've uninstalled Copilot and disabled AI in all local applications including the browser itself for exactly the reason described in this article. There's no way to protect your data from such an AI confusion attack by design. AI cannot discern your prompts versus text in file. The fact that an AI enabled word processor or email app could follow instructions embedded in a run-of-the-mill document or email is insane. Switching to Linux, BSD or another open source operating system is the only real solution to this problem.
  • officeplant 23 minutes ago
    Look on the positive side, the faster AI causes more harm the faster our bosses might wake up and push anti-AI company policies!

    Oh who am I kidding, ya'll asked for this reality. I will take great joy in the suffering from my AI-less soapbox.

  • nticompass 1 hour ago
    It's VBScript/macro worms all over again!
    • proactivesvcs 37 minutes ago
      Except turning off macros means losing our precious slop generators! Won't someone think of the fossil fuel industry?
  • piker 37 minutes ago
    White text still works!

    There are many approaches today. Check out https://tritium.legal/blog/noroboto where we tricked frontier algorithms into reading different Unicode values from those presented by the fonts in the document.

  • richardstahl 11 minutes ago
    History does not repeat but it rhymes. Strong Macro Virus vibes incoming!
  • teodosin 1 hour ago
    I may be naive here but can the hidden text not be flagged or outright removed before being passed to copilot? Why would there not be consideration for what a human user can see, especially if the hidden text was added by copilot in the first place?
    • lelanthran 4 minutes ago
      > Why would there not be consideration for what a human user can see,

      How would a machine actually know which part of a document a human can see unless they print it to PDF, scan the rasterised PDF and compare the result from the OCR with text in the document?

      I mean, I dunno how Word would decide that the following can't be seen by a user: white-on-white text, rendering off-page, embedded font with no lines, text covered by an image, etc.

    • yorwba 37 minutes ago
      There are many ways to hide text. Low contrast, small font size, image covering part of the text, too-small box cutting off some parts, custom font making certain words look like other ones... Alerting the user about such formatting issues would be helpful (e.g. also when you try to redact something by drawing a black rectangle over it without removing the text underneath) but you probably shouldn't rely on it for security.

      As long as Copilot can't be prevented from acting on instructions in its input, it would be safer to not make untrusted document content part of the input, similar to how macros in untrusted documents aren't executed by default.

  • dev_l1x_be 47 minutes ago
    I am wondering when the whole Excel/Word universe is going to die. One can only hope.
    • slfnflctd 2 minutes ago
      It seems to me it's more about Outlook, OneDrive, SharePoint, Project and Teams now. With Entra and Intune, of course. All kinds of 'control and monitor your employees' stuff has been going on there for a while. I think that's more of the moat than a spreadsheet and a word processor.

      Unless it's a shared document, no one cares if you use LibreOffice or whatever else, as long as you can provide requested formats when copying others that aren't mangled.

  • nottorp 52 minutes ago
    By the way, this is the method that uni professors have been using to catch students using LLMs to do homework.

    Paste any document in any LLM and you'll risk that, it's not something Microsoft specific.

    • lelanthran 10 minutes ago
      > By the way, this is the method that uni professors have been using to catch students using LLMs to do homework.

      I'm curious how that will work.

      Maybe the hidden instruction is to embed a shibboleth into the output?

      Maybe along the lines of "Also work in the phrases 'in respec off' as a mispelling of 'in respect of', 'its a doggy dog world' as a mispelling of 'its a dog eat dog world', and 'for all intensive purposes' as a mispelling of 'for all intents and purposes'"

      Is there any other way? "Lean heavily into AI tells that pangram will pick up easily.", or "In the second paragraph, use an analogy from Discworld" might work too.

    • Canopy9560 47 minutes ago
      That is correct. Really, the only "new" thing is the propagation part
  • skybrian 1 hour ago
    Why is it possible to have hidden text in a Word document? Why should the AI have access to that text?
    • layer8 56 minutes ago
      As the sibling comments illustrate, “hidden text” isn’t well-defined, and it has legitimate purposes that end users consciously make use of. The AI needs access to it, for one because the user might actually want the AI to perform actions on the hidden text (not in the sense of following instructions stated in the hidden text, but in the sense of manipulating the hidden text as part of the document), and also because otherwise it might cause breakage in the document if the AI doesn’t consider the presence of the hidden text when manipulating the document.

      What AI tools really need is reliable power-user levels of awareness about Word features, and corresponding structured access.

    • quietbritishjim 59 minutes ago
      Because, in the 1990s, you would print out your document before giving it to someone else to read. In those times, sometimes you'd want to include text in the document that shows while you're editing it (e.g. notes to yourself or draft text you might want to refer to later) but not when printed.

      I believe you would see hidden text by default (but this was a long time ago and I may have misremembered) when in "normal mode" (later "draft mode" and now removed entirely), which was the default view and showed a long continuous stream of text without the computation expense of calculating page break locations. But when you switch to "print layout mode" (now the usual view unless you're in reading mode) it would be hidden, so you could see what the document would be like printed, unless you explicitly turned on the display of hidden text in that mode.

    • yoz-y 1 hour ago
      It’s the good old white text on white background. Not really a way to defend against this, except having a no-style or high contrast mode that people actually use. Maybe some warning that would trigger if text is too small, off page or has very low contrast would help?
      • skybrian 57 minutes ago
        It seems like there could be a filter so that the AI can only see the text when it’s clear that a user could read it, and it’s okay if the AI misses some text. This might involve actually rendering it, though.
        • Bootvis 5 minutes ago
          Rendering followed by OCR and making sure that the computer doesn’t see more or less than the user does. Tricky and computionally more expensive.
    • Ekaros 1 hour ago
      Headers, footers, notes, comments, alt text, probably dozen of other features. Documents often are lot more than just markdown so properly to support everything you do have a lot of ways to hide text for various use cases.
      • quietbritishjim 31 minutes ago
        These are types of text that are, to some extent, effectively hidden. But I don't think that's what the article is talking about.

        Word has a feature literally called "hidden text". Select some text, go to the font properties dialog, click "hidden" and OK, and watch the text disappear.

        Edit: actually, this is white text on a white background as others have said, not true hidden text.

    • skywhopper 1 hour ago
      The LLM is reading the bytes of the file, not looking at a picture of its rendering. File metadata exists as well, and change history. Tons of places to hide text.

      Even if you processed it via a screenshot, image files are processed byte by byte as well and can contain textual metadata.

    • doublerabbit 1 hour ago
      The same reason to why you let AI have access to your filesystem. Idiocy, you need to teach AI to be smart somehow.

      You train a monkey to learn from a bunch of lower level intelligence monkeys. The same applies for AI. Just this time we are the monkeys.

  • anon48293 1 hour ago
    “ At the time of publication, no robust mitigation for the broader vulnerability class is available.”

    Well, that sounds promising..

    • ptx 32 minutes ago
      Well, yes. That LLMs are unable to distinguish instructions from data is a well-known and unsolved problem with LLMs in general.

      This is one of the reasons it would be completely insane to give LLMs access to your data or rely on them for important tasks. But apparently that doesn't stop people from doing it anyway.

  • utopiah 56 minutes ago
    3 months from first contact to... nothing. Surely those big corps peddling AI dev can't be taken seriously.
    • Canopy9560 48 minutes ago
      Microsoft, and MSRC in particular, have been hands-on and very responsive from the get-go. I think this problem is better viewed as a current LLM technology problem in general. Several mitigations have already been implemented that dramatically reduce the attack surface and propagation frequency. However, in general I think this is a real problem with no real solution yet.
      • iamniels 26 minutes ago
        * with no easy and free solution yet.
  • RaSoJo 1 hour ago
    Oh but for an alternative to Excel

    Purged I would have

    All things Microsoft from my (controllable) world

    • rnd0 37 minutes ago
      I'm a simple user so libreoffice (Calcs, in this case) suits my needs -but I'm also not using it for work, either.
    • asdff 35 minutes ago
      R
  • woadwarrior01 1 hour ago
    Could this possible be the first AI worm? Or are there any priors to this?
    • Canopy9560 1 hour ago
      Morris II(https://arxiv.org/abs/2403.02817) did demonstrate worming behaviour, so the concept at least is not new. However, I do not know of any similar demonstration in a commercial productivity product like Word.
    • SkyBelow 28 minutes ago
      Hmm... does this mean we could see AI worm evolution now?

      In the past, a worm couldn't really evolve unless it was coded to do so, and only to the extent it was coded. But an LLM worm, which instructs the LLM to copy the instructions elsewhere, will have slight random changes made as different LLMs will not always copy it perfectly. If a counter measure is deployed, and one of this alterations allows a miscopy to survive and keeps spreading, it feels like we have hit a much more natural case of evolution of a worm than ever before.

      One might even argue it is the most natural case of evolution in software because the evolution was never intentionally designed. The worm wasn't made to evolve, the LLM wasn't made with the idea of helping the worm evolve, the task trying to end the worm was done with the intent of the worm evolving. While all steps are human done, evolution wasn't intended by any of them, so if it does happen, it makes it a bit more 'natural' than every simulated evolution algorithm before it.

    • nottorp 54 minutes ago
      First LLM worm.
  • westurner 25 minutes ago
    Yesterday I was reading model thinking output and learned that the model has concerns about shell backticks in commit messages.
    • igregoryca 6 minutes ago
      That's what thinking output is for, right? Mixing random tokens that live roughly in the same semantic realm, throwing them at the wall, and seeing what sticks? Hopefully, this backticks concern didn't stick.
  • josefritzishere 29 minutes ago
    It's increasingly clear that AI needs to be heavily regulated to be safe for public use. It needs to grow out of it's "wild west" model.
    • watwut 11 minutes ago
      This has nothing to do with "model" being unsafe or too powerful or whatever else excuse Antropic wants to use to ban competition.

      This is equivalent of sql injection and normal worm.

  • idiotsecant 1 hour ago
    LLMs should be viewed with the same terror as a reckless toddler who knows some bash syntax. Deeply embedding them into important and privileged systems will be the end of us.
  • ghlancet 1 hour ago
    I mean all your data is already exfiltrated to Copilot, so a little extra worm cannot hurt.

    It is fun to see how all AI narratives are collapsing.

    • Sleaker 36 minutes ago
      I think the damage/risk here isn't explicitly about exfiltration, but could also just be damage/harm to the organization through re-writing content in documents.
  • Canopy9560 1 hour ago
    Author here.

    This post covers a coordinated disclosure with Microsoft (MSRC) regarding a vulnerability class that allows attacker-controlled instructions in an attached document to hijack Copilot for Word.

    It manipulates the AI to alter the output text (e.g., halving financial figures) and append the attack prompt into the new document concealed as white text.

    Because the downstream document now carries the payload, it acts similarly to an AI worm across normal user workflows. Microsoft deployed multiple fixes over a 144-day coordination period, but the broader vulnerability class remains unmitigated and exploitable because it exploits fundamental limitations of current LLMs.

    When attacker instructions are combined with legitimate information the model's context window, the tokens being inspected participate in the act of inspection, meaning current LLM architectures provide no reliable boundary between intention and interpretation.

  • KolibriFly 31 minutes ago
    [flagged]