Rogue AI agents from OpenAI and Anthropic have again been caught trying to disrupt servers and software—and leaving ...

The UK AI Security Institute says OpenAI’s and and Anthropic’s models engaged in deceptive behavior and harmful activity ...

Researchers from OpenAI said the company is “dramatically scaling up” its security efforts after discovering that two of its models orchestrated a hack without human prompting last month.

Groups of hackers are breaking into large U.S. financial firms to steal sensitive data and extort victims, Google’s security ...

It's learning from us.

According to a report from the UK’s AI Security Institute, which evaluates frontier models from top AI labs before they are ...

The AI models tested carried out “unsanctioned” actions — including hacking a website and attempting to inject harmful code ...

OpenAI also designates an LLM as Critical if it can launch cyberattacks against hardened systems based on only a high-level ...

Researchers found that widely used lab machines produced digital DNA files that are vulnerable to tampering.

This time, it was third-party AI testers that spotted Claude and GPT models trying to hack real companies and organizations.

According to OpenAI, the models decided to solve a cybersecurity exercise by hacking out of the environment in which OpenAI ...

Federal and state officials are racing to address an assault on the nation’s water supply that they believe is the work of ...