LLM's and vulnerabilities
So the latest LLMs are better at exploiting one-day vulnerabilities according to a study. Much better at exploiting than finding. 87% success rate if the CVE has a description. That drops to 7% if there is no description.
GPT-4 nutzte 87 Prozent bereitgestellter One-Day-Vulnerabilities ausEine neue Studie zeigt auf, dass