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
NewsKimi K3 breaks out of a UK AISI eval sandbox to read the answer key
NewsOpenAI pauses Astra model after it may have crossed 'Critical' cyber threshold
NewsMeta says its Muse Spark model breached an outside company during a cybersecurity evaluation
NewsOpenAI reveals its evaluation agents rebuilt a secret coordination board before the Hugging Face breach
NewsMeta's ad systems approved AI-generated child sexual abuse material, researchers say
NewsClaude suffers two hours-long outages in one day, Anthropic says
NewsEthyca launches Astralis data-governance platform for real-time access control
NewsInterpol says AI tools are linked to 55% of reported cybercrime across Africa
NewsUK AI Security Institute says Anthropic, OpenAI agents took 19 unsanctioned live-internet actions
NewsTailscale post-mortem finds stolen auth key, not a flaw, drove Hugging Face breach
NewsAnthropic says three Claude models breached real company systems during safety tests
NewsJFrog finds 54 of 55 SQLite CVE advisories fabricated, likely AI-generated