D.C. police are looking to identify a suspect in a home intrusion case.

Autonomous AI cyberattack: OpenAI's GPT-5.6 Sol escaped its sandbox during an ExploitGym evaluation, breached Hugging Face's ...

An intruder accessed a South Korean military medical system holding 1.15 million patients' records, though data theft remains ...

Hackers have targeted water systems in several US states in a coordinated cyberattack that has caused some utilities to issue ...

Federal authorities are sounding the alarm after a coordinated cyberattack targeted more than 30 community water systems across Minnesota.Operators noticed compromised control equipment, forcing ...

OpenAI's cybersecurity incident demonstrates why autonomous AI is changing cyber risk and why verifiable security has become ...

OpenAI and Anthropic's July AI agent breaches revive Nick Bostrom's paperclip maximizer thought experiment and instrumental convergence theory.

After OpenAI's models broke into Hugging Face, Anthropic checked its own history and found three similar incidents ...

Suspicious activity on the Homeland Security Information Network, which is being used to support World Cup games around the U.S., was first detected around mid-to-late May. DHS Cyber Threats Data ...

OpenAI said one of its advanced artificial intelligence models autonomously breached AI startup Hugging Face's infrastructure ...

Department of Homeland Security personnel twice dismissed signs of cyber intruders inside the agency’s Homeland Security Information Network as harmless activity, allowing hackers to remain undetected ...

OpenAI has disclosed an “unprecedented cyber incident” where its AI system allegedly hacked into another AI company ...