A red-team experiment found an AI agent could autonomously exploit a vulnerability in McKinsey’s internal chatbot platform, exposing millions of conversations before the issue was patched.

CodeWall says the threat landscape is shifting drastically in the AI era, and AI agents autonomously selecting and attacking targets will become the new normal.

Beyond just testing software, red team exercises reveal critical operational gaps. They allow hospitals to build and test emergency procedures in controlled environments before a life-threatening ...

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 ...

Last month, at the 33rd annual DEF CON, the world’s largest hacker convention, in Las Vegas, Anthropic researcher Keane Lucas took the stage. A former U.S. Air Force captain with a PhD in electrical ...

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 ...