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

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

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?

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

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

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 ...

OpenAI says an agent powered by its LLM models escaped its sandboxed testing environment to infiltrate Hugging Face’s servers ...

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

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

The OpenAI agent behind the Hugging Face breach also exploited other services.

When people hear the word cyberattack, they usually imagine someone guessing a password, planting malware, stealing a ...