Re:Getting Pwn'd by AI: Penetration Testing with Large Langu...
by kingsomething on Tuesday August 08, 2023 @03:31AM
(#37045690)
Vision paper that connects gpt-3.5-turbo with vulnerable VM over SSH and asks 'it' to become root. A follow-up paper creating a better vulnerable VM benchmark and retesting results with gpt-3.5, gpt-4 and local LLMs seems to be in the works
[ Parent
| on HN ]
There are no comments on this comment yet.