Most of the attempts on the US government websites appear to have been unsuccessful, but the OpenAI agents sought to find ...

A security breach at the FBI, claimed by ShinyHunters, has exposed the personal information of current and former employees, ...

Chinese actors are deploying thousands of LLM gateways to clone U.S. frontier models, share credentials, and bypass ...

Google is now months behind its competitors in reporting its "rogue" AI models to the public, but says that its incidents ...

A rogue OpenAI agent was once again responsible, finding and taking advantage of what appeared to be a serious weakness in ...

Double-extortion ransomware gang ShinyHunters has hacked its rival, Cl0p, and defaced its Tor-based data leak site after ...

Cyber resilience has become the industry’s favorite word, but few of the organizations using it can show they would survive a ...

New papers from OpenAI discussing the rogue actions of their AI models are becoming almost a weekly feature at this point. The latest of these, titled "Our framework for reporting model misalignment," ...

As attackers use AI and automation to move from access to impact faster than traditional SOC workflows were designed to handle, security teams need technology that can operate at comparable speed.

Ask any A&D CIO what keeps them up at night and legacy code comes up before budget every time. Cleared talent is scarce, supply chains run through a dozen countries, and the AI everyone wants can’t ...

In the wake of the news that out-of-control AI agents had overwhelmed an obscure message board and used it to plot attacks some months before the Hugging Face incident, researchers have found that ...