Protecting artificial intelligence systems across their entire lifecycle, from securing training data integrity all the way to defending against adversarial attacks
65 articles
A Chinese cybersecurity executive claims to have developed an AI system with Mythos-comparable vulnerability discovery c...
Read MoreThe MCP Enterprise-Managed Authorization extension is now stable, with Anthropic, Microsoft, and Okta among the first ad...
Read MoreIBM's Martin Keen breaks down the four memory types every AI agent needs — working, semantic, procedural, and episodic —...
Read MoreThe FBI is warning organizations about Kali365, a $250 phishing-as-a-service kit that captures Microsoft 365 OAuth token...
Read MoreFable 5's safeguard architecture introduces classifier-based fallback to Opus 4.8 instead of outright refusals, a new 30...
Read MoreAnthropic published a 35-page Zero Trust framework for agentic AI covering three capability tiers, eight implementation ...
Read MoreUsers report continued Instagram account compromises hours after Meta claimed the AI chatbot vulnerability was fixed. Se...
Read MoreHackers hijacked Instagram accounts by tricking Meta's AI support chatbot into bypassing email verification. The attack ...
Read MoreClaude Mythos, Anthropic's most powerful model, can automatically develop functional cyberattacks at professional level....
Read More