20 comments

  • simonw a day ago ago

    This is fascinating - there is a TON of detail in here about how OpenAI's rogue agent exploited Hugging Face.

    A few details that stood out to me:

    1. Having found a way through the OpenAI container network proxy, it exploited an "unsecured public code-evaluation sandbox hosted on a third-party provider's infrastructure" - that gave it a box it could run the rest of the attack from.

    2. At one point it used a Jinja2 template exploit:

      {{ cycler.__init__.__globals__.__builtins__.exec(
         "import gzip,base64; exec(gzip.decompress(base64.b64decode('<payload>')))"
       ) }}
    
    3. It monkey-patched a DNS resolver at one point to return a hard-coded IP:

      orig = socket.getaddrinfo
      socket.getaddrinfo = lambda *a, **k: [(2, 1, 6, '', ('<pinned-ip>', 443))]
    
    4. At one point it used Tailscale!

      tailscale --tun=userspace-networking --state=mem: --socket=/tmp/ts.sock \
       --socks5-server=127.0.0.1:1055 --no-logs-no-support >/tmp/td 2>&1 &
  • ghm2199 3 hours ago ago

    What is truly more scary is the fact that typically powerful models are trained on a constitution(Anthropic)/Model Spec(OpenAI) when doing there RL/RLHF. That gives it its persona of a "helpful assistant". Its the mask. Weak as it is its all that stands between the model refusing vs doing your bidding — or worst its own bidding when set about on making a widget X.

    Its also well known in academic research, that if you try to finetune the model to be more pliant for one end e.g. "Be helpful with analyzing cyber security threats", affects an unrelated part of its personality to do with safety e.g. talking to humans about mental health. Look at these excerpts that demonstrate such things from the blog:

    > We believe the entire intrusion was, from the agent's point of view, an attempt to cheat the evaluation: reach our production systems and steal the test solutions rather than solve the challenge on its own.

    > The models we reached for first, Claude Opus and Fable, refused a large part of that work: their safety guardrails treated reverse-engineering an exploit the same as launching one.

    • ghm2199 2 hours ago ago

      And with newer open models gaining vast capabilities every day, it would behoove the government to put regulations on all such releases to opensource the constitution on which they are trained. It won't stop people from distilling and fine-tuning stupidly unsafe models, but it might give infrastructure a fighting chance against such cyber threats from what there is now.

  • SaucyWrong 16 hours ago ago

    Something about this attack that has been unsettling to me is that without safety refusals the model did a lot of interesting counter-security work in order to cheat on the requested evaluation. Like, it demonstrated interesting exploit achievements because it didn’t “feel like” doing the exercise, which is unsettling because presumably it could do the same thing with any work I tried to delegate to it, and might in fact be pre-disposed to doing that.

    • spwa4 9 hours ago ago

      Come on. 3 brilliant compromises essentially giving full access to huggingface internal systems, source code, AWS accounts (at least), and a number of old admin accounts, followed by a huge haystack of significantly less smart actions flailing about, almost bored.

      Here's a thought: maybe they haven't found the needle that the haystack is there to hide.

      • dgellow 36 minutes ago ago

        Could be the difference in behavior between the main agent and subagents that don’t have the rest of the context? Just a thought

    • joshka 11 hours ago ago

      [flagged]

  • llama052 19 hours ago ago

    It’s a little concerning to me that it appears that openAIs sandbox consists of a web proxy and not stronger controls that would actually isolate traffic and report patterns to whoever is responsible for overseeing these research models. It should border on closer to an air gap network more so than a proxy.

    I would argue that it's negligence and that's aside from the fact that if a human did this there would actually be repercussions.

    • dgellow 34 minutes ago ago

      It’s definitely negligence given how they talk about their product. They are either lying when they talk about their fears, or don’t actually take it seriously enough to use serious guardrails. It’s very concerning

    • simoneree 11 hours ago ago

      [dead]

    • joshka 11 hours ago ago

      The exploit gym setup explicitly allowed access to package registries and v8 sources. Putting a cache on that doesn't seem like a bad idea generally, except when there's a 0-day in the cache :D But yeah, for this sort of thing I'd be locking down very specific egress things and putting alerts on it that are entirely outside of the red network.

      > I would argue that it's negligence and that's aside from the fact that if a human did this there would actually be repercussions.

      I’m not sure “negligence” follows just from the controls turning out to be insufficient. Research involves mistakes, especially around novel failure modes. The question is whether the precautions were unreasonable given what they knew at the time, rather than whether hindsight suggests stronger controls would have helped. Doing it twice though would be negligent.

      Caveat: I’ve worked with some of the people involved, so I’m probably biased toward a charitable reading.

      • llama052 3 hours ago ago

        “Research” generally doesn’t involve actively hacking third party systems though.

  • heaney-555 10 hours ago ago

    Where are all the "this was just a marketing stunt" people now?

    • applicative 3 hours ago ago

      they are praising xi, that friend of humanity, for releasing weights for kimi k3