Protecting artificial intelligence systems across their entire lifecycle, from securing training data integrity all the way to defending against adversarial attacks
92 articles
LiteLLM, the Python library with 95 million monthly downloads powering nearly every AI agent framework, was compromised ...
Read MoreThe UK AI Safety Institute's independent evaluation of Claude Mythos Preview reveals critical nuances missing from vendo...
Read MoreAI agents integrated with GitHub Actions can be hijacked via prompt injection to steal API keys and tokens. Anthropic, G...
Read MoreWhile healthcare debated AI governance, adversaries built autonomous attack systems. GTG-1002—the first documented AI-or...
Read MoreAnthropic's unreleased Claude Mythos Preview model found thousands of zero-day vulnerabilities across every major OS and...
Read MoreAI coding assistants let developers write code faster than ever—but speed decouples volume from understanding. IBM's Pat...
Read MoreTraditional authentication breaks down with agentic AI. IBM's Grant Miller explains how token delegation, actor-plus-sub...
Read MoreAnthropic accidentally shipped Claude Code's entire source code to npm on March 31, 2026. Combined with a concurrent axi...
Read MoreGoogle Cloud's security teams just released their Cybersecurity Forecast 2026, predicting AI will transition from except...
Read More