A recent series of cybersecurity competitions organized by Palisade Research shows that autonomous AI agents can compete directly with human hackers, and sometimes come out ahead.
  • In two hacker competitions run by Palisade Research, autonomous AI systems matched or outperformed human professionals in demanding security challenges.
  • In the first contest, four out of seven AI teams scored 19 out of 20 points, ranking among the top five percent of all participants, while in the second competition, the leading AI team reached the top ten percent despite facing structural disadvantages.
  • According to Palisade Research, these outcomes suggest that the abilities of AI agents in cybersecurity have been underestimated, largely due to shortcomings in earlier evaluation methods.
  • JayDee@lemmy.sdf.org
    0·
    5 days ago

    Hey, uh, Palisade. Maybe it’s a bad idea to be training AI systems to hack? Like having the ability to just pump out automated hack-bots that outperform human hackers is kind of a terrible idea that could lead to a computer-internet infrastructure collapse at worst?