The LiteLLM Breach and the New Reality of AI Infrastructure On March 24, 2026, the Python Package Index (PyPI) hosted malicious versions of the LiteLLM library—specifically 1.82.7 and 1.82.8—for ...

CISA says attackers are exploiting a critical 2025 vulnerability in Ray, the widely used open source framework for scaling Python and machine-learning workloads. Tracked as CVE-2025-62593 and rated 9.

Security researcher Kevin Beaumont got a call last week from a major US technology company that insisted it had nothing to worry about: all the credentials stolen in March's LiteLLM supply chain ...

When we think about security threats, we generally imagine them coming from far away across the wider internet. But what if the connection between you and your ISP was the target? [Rithwik ...

The flaws in Zoom could let someone in a meeting take control of another participant’s device without the victim clicking anything.

A recent series of cyberattacks on U.S. water systems has exposed vulnerabilities across critical infrastructure during the ...

Las Vegas was hotter than hell last week, but not as hot as the market for artificial intelligence-enabled security at Black ...

Agentic AI armed attackers first, but it also put real building power in defenders’ hands. Here’s what security practitioners built in two days at Black Hat USA 2026, and how the CyberAgents Exchange ...

Contrast Security has launched CVE Shield, a runtime control that detects, monitors and blocks exploitation of known vulnerabilities in production ...

AI models are finding thousands of zero-day flaws in minutes, forcing defenders to adopt automated, real-time virtual ...

Everyone talked about autonomous agents. Almost nobody examined the two injection vectors that turned Hugging Face's dataset-processing pipeline into a production foothold.

OpenAI and Anthropic say their models broke into other companies' systems during testing, raising security concerns amid a heated debate over how to regulate AI.