Unrelenting, persistent attacks on frontier models make them fail, with the patterns of failure varying by model and developer. Red teaming shows that it’s not the sophisticated, complex attacks that ...

Shellter Project, the vendor of a commercial AV/EDR evasion loader for penetration testing, confirmed that hackers used its Shellter Elite product in attacks after a customer leaked a copy of the ...

In case you missed it, OpenAI yesterday debuted a powerful new feature for ChatGPT and with it, a host of new security risks and ramifications. Called the "ChatGPT agent," this new feature is an ...

Researchers at red-team security startup CodeWall say their AI agent hacked McKinsey's internal AI platform and gained full read and write access to the chatbot in just two hours.… It's yet another ...