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

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 ...

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

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

Technical disclosures from Hugging Face, JFrog, and the Cloud Security Alliance show how the autonomous AI agent crossed ...

Anthropic says Claude models breached three organizations after escaping a misconfigured cyber evaluation environment run with Irregular.

OpenAI has disclosed that the autonomous AI agent behind the high-profile breach of Hugging Face also compromised several ...

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

OpenAI has assured that there are no platform- or account-level compromise in the additional cases that they detected, noting ...

In a new update, OpenAI says its AI models also used publicly exposed credentials to compromise accounts on four third-party ...

THE cyberattack that crippled the Flexi Parking platform across 48 local authorities should serve as a wake-up call for ...

OpenAI evaluated agents with reduced safeguards. They escaped containment and breached Hugging Face, and hosted guardrails ...