Large language models are now capable of automating attacks that were previously only possible by human adversaries. In this talk, I discuss several ways that adversaries could mis-use current models in order to cause harm both at a larger scale and at a lower cost than they do currently. For example, we find that recent state-of-the-art models can now find 0-day vulnerabilities in large software projects that have been extensively tested by humans for decades. These new capabilities will alter the threat landscape and require we rethink security in the coming years.

all 10 comments

sorted by: hot top controversial new old
[–] 31 points 7 months ago

this is an ad

  • source
  • [–] 17 points 7 months ago

    I'm tired of the bullshit ads disguised as "experts" and "studies"

  • source
  • [–] 7 points 7 months ago (3 children)

    That headline doesnt parse for me

  • source
  • hideshow 3 child comments
  • [–] 6 points 7 months ago* (last edited 7 months ago) (1 child)

    This guy who's job expertise is cyber security and LLMs is very very worried. The models are improving exponentially and finding very advanced vulnerabilities now. This is a serious problem.

    "To Black Hat" = hacking

  • source
  • parent
  • hideshow 1 child comment
  • [–] 1 point 7 months ago

    A black hat is a malicious(evil) hacker. The goal is unauthorized access of remote computer systems, typically. The closer to root the better.

    A grey hat is a neutral hacker. Probably mostly a curiosity, no good or bad intent. Perhaps like someone who's trying to reverse engineer a game console because they own a lot of games and they're just curious how it all works. Or someone that just wants to make a backup of a movie (circumvent DRM.)

    A white hat is a benevolent hacker that seeks to fix exploits that black hats use to perform their crimes. And they often target the greys(but usually the lawyers are more effective there.)

  • source
  • parent
  • [–] 4 points 7 months ago

    AI has achieved rank: script kiddy

    Y'all got any interesting news?

  • source
  • [–] 3 points 7 months ago

    Just use the same AI to white hat. 🤷‍♂️

  • source
  • [–] 3 points 7 months ago (1 child)

    Remember when AI outclassed the best Go player in the world?

    That was in 2016.

  • source
  • hideshow 1 child comment
  • 1 comment in c/selfhost@lemmy.ml view that post
    [–] [S] 1 point 6 months ago

    Have you all tried running them against any open source software you use?

  • source