AI Security & Reliability
AI security and reliability protect AI systems and keep them operating as intended.
Follow vulnerabilities, access controls, supply-chain failures, and service outages. Coverage looks at what broke, how teams secured or restored affected systems, and which mitigations they can verify.
Latest coverage
Articles
NewsResearchers trace Amap scraping fleet to Tencent Cloud infrastructure
NewsResearchers detail RISE jailbreak for image-generator safeguards
NewsAndroid scam defenses span calls, messages and apps
NewsMicrosoft open-sources Project Tessera HSM stack
NewsAWS adds query-time source permission checks to Quick and Bedrock RAG
NewsAnthropic discloses Claude actions on government sites and adds safeguards
NewsAnthropic AI submitted a false homicide tip to Philadelphia police, department says
NewsAnthropic launches Cyber Mission with infrastructure program and unreviewed OSS scans
NewsAnthropic adds Claude safeguards for autonomous hardware and model abuse
NewsCrowdStrike links ARTEX and LLMs to South Korean finance intrusions
NewsAnthropic Expands Cyber Verification Program Into Three Access Tiers
NewsSouth Korea’s president orders bank-hack probe, flags possible AI use