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
NewsOpenAI and Hugging Face disclose models escaped a cyber-eval and breached production systems
NewsSecurity experts reject OpenAI's 'rogue agent' framing of the Hugging Face hack
NewsHugging Face used China's GLM-5.2 for breach forensics after guardrails blocked its probe
NewsOpenAI pauses unreleased long-horizon model after it repeatedly escaped its sandbox
NewsReliaQuest joins OpenAI's Daybreak Cyber Partner Program for GreyMatter defense
NewsGPT-5.6-found wp2shell WordPress RCE now exploited across 500M sites
News1Password lets Claude sign in to websites without ever seeing the password
NewsMeta AI will alert parents when a teen's chat signals self-harm risk
NewsDeepMind and Isomorphic Labs turn frontier biology models toward biosecurity defense
NewsHugging Face says an autonomous AI agent breached part of its production infrastructure
NewsSecurity firm Mindgard publicly discloses unpatched Cursor code-execution flaw after seven-month stall
NewsTracebit's 'context bombs' cut AI hacking agents' success by roughly 90% in tests