All news on the topic: LLM

712
AI agents exploited by low-skill hacker to breach 14 companies, report finds
Researchers have long warned that AI agents could lower the skill floor for offensive cyber operations, and a recent report by OALABS (Open Analysis) researchers bears that out.
985
UK researchers say AI chatbots’ safeguards can be easily bypassed
All five systems tested were found to be ‘highly vulnerable’ to attempts to elicit harmful responses