AI agents outperform human teams in hacking competitions (the-decoder.com)
from Pro@programming.dev to cybersecurity@infosec.pub on 01 Jun 14:01
https://programming.dev/post/31425481

  • 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.

#cybersecurity

threaded - newest

JayDee@lemmy.sdf.org on 01 Jun 23:46 collapse

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?

danzabia@infosec.pub on 02 Jun 18:11 collapse

I think they would agree with your assessment.