• Bubbey@lemmy.world
    link
    fedilink
    English
    arrow-up
    2
    ·
    1 hour ago

    I’m sure nothing will go wrong with tons of critical business documents being routed through copilot for organizations…

  • Nate@piefed.alphapuggle.dev
    link
    fedilink
    English
    arrow-up
    78
    arrow-down
    2
    ·
    1 day ago

    $10 says they haven’t actually escaped anything and it’s just hallucinating a directory structure & file contents

    • communism@lemmy.ml
      link
      fedilink
      English
      arrow-up
      26
      arrow-down
      1
      ·
      24 hours ago

      MS said they fixed it and categorised it as a “moderate severity vulnerability” so presumably they did in fact gain root access to the container

      • wewbull@feddit.uk
        link
        fedilink
        English
        arrow-up
        14
        ·
        22 hours ago

        If they gained root access to the container, that’s not a moderate vulnerability. Root inside a container is still root. You can still access the kernel with root privs and it’s the same kernel as the host.

        Docker is not a virtual machine.

        • Fizz@lemmy.nz
          link
          fedilink
          English
          arrow-up
          1
          ·
          6 hours ago

          I think they gained root to the python env which they couldn’t do anything with because it was still running in docker inside a VM.

          • According to a smart sounding fella on hacker news.
        • communism@lemmy.ml
          link
          fedilink
          English
          arrow-up
          9
          ·
          18 hours ago

          I know that? I’m just saying that MS categorised it as such. It would be strange to include the part about MS’s responses if MS also found that the vulnerability was not what the researchers claimed it was.

          • wewbull@feddit.uk
            link
            fedilink
            English
            arrow-up
            6
            ·
            9 hours ago

            What I’m saying is something about the story doesn’t add up.

            Either Microsoft classified a major issue as a minor one so they didn’t have to payout the bug bounty (quite possible), or the attack didn’t achieve what the researchers thought it did and Microsoft classified it according to it’s actual results.

    • MagicShel@lemmy.zip
      link
      fedilink
      English
      arrow-up
      25
      ·
      1 day ago

      Even if it had access to its own source during training, the chances of it regurgitating it with total fidelity are zero.

  • ignirtoq@fedia.io
    link
    fedilink
    arrow-up
    25
    ·
    1 day ago

    Several years ago I created a Slack bot that ran something like Jupyter notebook in a container, and it would execute Python code that you sent to it and respond with the results. It worked in channels you invited it to as well as private messages, and if you edited your message with your code, it would edit its response to always match the latest input. It was a fun exercise to learn the Slack API, as well as create something non-trivial and marginally useful in that Slack environment. I knew the horrible security implications of such a bot, even with the Python environment containerized, and never considered opening it up outside of my own personal use.

    Looks like the AI companies have decided that exact architecture is perfectly safe and secure as long as you obfuscate the input pathway by having to go through a chat-bot. Brilliant.

  • BaroqueInMind@piefed.social
    link
    fedilink
    English
    arrow-up
    14
    ·
    1 day ago

    And so Microsoft decided this wasn’t a big enough vulnerability to pay them a bounty. Why the fuck would you ever share that with them then, if you could sell it to a black-hat hacking org for thousands?