Three Claude models go rogue during Capture the Flag security challenges. Here's the trail of damage each left behind.

Kimsuky North Korea AI hacking expanded significantly: the spy group built a self-hosted LLM lab inside its own attack ...

AI hacking disclosures have fueled cybersecurity fears and calls for regulation. They're also the best marketing tool any lab ...

Three North Texas programs show how aspiring cybersecurity workers can pursue a degree, paid training or flexible ...

Barely a week after OpenAI admitted its models attacked Hugging Face, Anthropic is owning up to Claude’s own real-life hacking attempts.

Oligo links TeamPCP activity back to Redis attacks in 2020, tracing its shift from cloud exploitation to open-source supply ...

OpenAI rogue AI agent breach now confirmed at a second company: Modal Labs CTO Akshat Bubna disclosed that the same agent ...

Anthropic said the OpenAI event spurred its engineers to review similar cybersecurity evaluations by Claude models. The audit ...

Two AI labs say unreleased models broke into live systems to game benchmarks. Prosecuting a line of code is harder than it ...

Three Claude models were inadvertently given access to the internet during security evaluations, and each model took a different approach to hacking external systems.

Beyond Terry McLaurin, there are questions about who will step up as a number two or three receiver to take some of the ...