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

Both major AI labs’ models broke containment, escaped onto the internet, and hacked other companies. If a human had done that, the law would likely be against them. But a bot?

Artificial intelligence models developed by OpenAI and Anthropic for cybersecurity testing escaped controlled environments and attacked unsuspecting companies, the Wall Street ...

In the aftermath of OpenAI’s attack on Hugging Face, experts say it’s time for everyone to take security far more seriously.

On this "Face the Nation with Margaret Brennan" broadcast, Democratic Sen. Mark Kelly and Republican Rep. Mike Turner join ...

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

Details have been released of an emergency call with hundreds of cyber-security experts after the ChatGPT hack of a tech ...

Artificial intelligence (AI) agents’ growing autonomy and cyber capabilities are shifting risk from theoretical misuse to ...

Hackers reportedly breached the Department for Education’s help desk and Turing Scheme portal, exposing contact details of ...

On risks, cybersecurity, and China, the biggest firms are losing the argument against open models.

TL;DR: Anonymous is targeting Sony over its plan to stop making physical PlayStation discs, warning digital-only purchases are licensed, revocable, and can be disabled despite being marketed as owned; ...

Two recent AI breaches raise worrisome questions about the industry: Will an AI one day hack into some vital computer network ...