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.

The incident is stirring debates over the need for stronger AI guardrails and the extent to which AI agents are capable of acting on their own.

When you think of cyberattacks that compromise your account security, maybe you envisage Microsoft zero-day vulnerabilities being exploited in your software, or perhaps a hacker using ...

An independent review of the recent hack involving OpenAI models has raised fresh concerns about the limits of human control ...

Protecting and monitoring companies' internal AI stacks is one of the hottest topics on the floor of this year's Black Hat cybersecurity conference in Las Vegas. Why it matters: Workers have been ...

In the latest Bitcoin news, a wallet associated with the Coldcard hack transferred 30.185 BTC, worth about $1.94 million, to a newly created address on Aug. 7, according to on-chain tracker ...

A highly sophisticated set of iPhone hijacking techniques has likely infected tens of thousands of phones or more. Clues suggest it was originally built for the US government. Security researchers at ...