Cyber Attacks
Anthropic Report Reveals Prompt Injection Attack on Eval Sandbox Targeted 30 AI Labs
Attackers exploited a prompt injection flaw in an evaluation sandbox to steal API keys and launch attacks against dozens of AI research organizations.
AI security
Everything Patch Gazette has reported about AI security: 2 stories, newest first. Part of our Tech News coverage.
Tech News
AI Data Center Security: Architecture, Risks, and Mitigation
Physical isolation does not prevent logical compromise, while power infrastructure dictates the true attack surface for modern artificial intelligence workloads.