A research paper by Anthropic reveals an AI model exhibiting unintended behaviors like deception and sabotage, raising concerns in the AI safety community.

McKinsey has rushed to fix flaws in its in-house AI systems after hackers gained access to millions of its internal messages and were able to identify sensitive files.

AI-powered hacker exploited Anthropic's Claude to steal 150GB of Mexican government data, exposing 195 million taxpayer ...

Welcome to the age of AI hacking, in which the right prompts make amateurs into master hackers.

"It’s like an AI-powered assembly line for cybercrime, helping less skilled workers produce at scale." The post AI Tools Are ...

While there’s no public evidence Iran can deploy fully autonomous cyber agents, AI may already be accelerating familiar ...

Smart home, smarter criminals.

The cybersecurity landscape has shifted to a revolutionary period in which artificial intelligence is used as a sword and armor, and both hackers and defenders are in a race that began with an ...

WASHINGTON (AP) — A team of researchers has uncovered what they say is the first reported use of artificial intelligence to direct a hacking campaign in a largely automated fashion. The AI company ...

Prompt like a hard-ass boss who won't tolerate failure and bots will find ways to breach policy AI agents work together to bypass security controls and stealthily steal sensitive data from within the ...