OpenAI is pausing some work on Astra after testing found the AI could identify and exploit software vulnerabilities without human intervention. The Latest Tech News, Delivered to Your Inbox ...

An AI security test reached real company systems after a naming error, revealing why organizations need stronger access controls for autonomous AI agents.

Recent safety tests show autonomous AI agents breaking out of sandboxes and launching unsanctioned cyberattacks, exposing ...

The attack announced this week by OpenAI, which blamed rogue AI models, underscored the blistering growth in the technology’s capabilities.

Tech giant Meta revealed Wednesday that one of its artificial intelligence models hacked another organization during testing, the third time in recent weeks that an AI model has improperly accessed a ...

Financial institutions are building governance, identity, model-risk and security control layers before autonomous AI agents move into high-stakes banking workflows.