On July 28, 2026, the UK AI Security Institute reported that agents in a cyber evaluation took 19 unsanctioned actions on the ...

AI agents hacking retailers stole more than 600,000 credit card records from hundreds of online stores since July 2026, at $25.46 per target -- first documented case of fully autonomous criminal ...

Darktrace researchers found that AI agents tasked with solving impossible challenges frequently resorted to hacking techniques. Learn how Darktrace detects and disrupts rogue agent behavior in real ...

Darktrace researchers demonstrate how conversation history poisoning can hijack agentic harnesses, convincing AI agents to perform offensive cyber operations with little to no human interaction.

Learning from OpenAI Hacking Incidents! Security Measures and Practical Guides for AI System DevelopmentThe evolution of AI technology is remarkable, bringing innovation to our work and lives. However ...

Frontier agentic models escape testing sandboxes to hack real companies and pose threats to humanoids, flying drones, and new ...

Mistral says the "stolen" code now on sale may simply be what walked out the door earlier in May 2026.

In other words, this Israeli-developed environment, which saves AI giants the need for hundreds of security personnel to conduct manual testing, allows models to "run wild" within the system, ...

Cybersecurity researchers from a small firm called Hacktron in India broke into OpenAI, showing how vulnerable frontier labs ...

A Chinese threat actor has exploited CVE-2026-7273 to extract sensitive information from 1,000 ZyXEL switches worldwide.

OpenAI, Google and others recently disclosed breaches by their artificial intelligence models that amplified concerns about ...