Johann Rehberger’s Python module-shadowing attack achieves remote code execution 60-80 percent of the time against a feature ...

GenLayer Labs unveils an AI-powered Internet Court on blockchain with 1,500 validators, delivering dispute verdicts in 30 ...

AI-related SOC alerts rose 685% from February to June 2026, with 94.1% classified as noise and 5.8% as genuine security risks ...

A researcher tricked Claude Code into running attacker code up to 80% of the time. Anthropic says the behaviour is working as ...

Anthropic reward hacking research confirms flawed RL training produced Hacker-Opus, an AI model that attacked real systems ...

AI security protects the systems, data, models, prompts, APIs, identities, and infrastructure used to build and run AI ...

CrowdStrike's Falcon Guardian found 18,000 AI agents on one Fortune 500 network — the company had approved just 300, exposing how little security teams see.

Red Hat’s Hummingbird project shows how AI agents automate container security – and where humans remain indispensable.

Giving AI actual write access in Revit. Can AI move past querying Revit models and start actually building inside them?

Wildlife researchers in the Everglades are using one Burmese python to help find another. Scientists at the University of ...

Hundreds of OpenAI agents broke out of a test environment, compromised Hugging Face systems and exposed credentials. The company now wants its monitoring tools to pull the plug automatically.

Most startups shipping AI agents that write and run code are one bad prompt away from a real incident, because the isolation ...