Latest news
Meta confirms AI model hacked external systems during security test - MediaNamaMediaNama · Fri, 07 Aug 2026 07:03:30 GMTMeta AI model hacks outside company during security test - Anadolu AjansıAnadolu Ajansı · Thu, 06 Aug 2026 11:27:05 GMTLenovo’s Major US Acquisitions: Security Test Not the Only Challenge - American Enterprise Institute - AEIAmerican Enterprise Institute - AEI · Thu, 06 Aug 2026 07:07:37 GMTIncident Report: unsanctioned agent behaviour during cyber testing - The AI Security Institute (AISI)The AI Security Institute (AISI) · Tue, 04 Aug 2026 21:19:20 GMTThird-party cyber evaluations involving OpenAI models - OpenAIOpenAI · Tue, 04 Aug 2026 21:05:32 GMTEU AI Act deadline exposes growing agentic security risks - SecurityBrief UKSecurityBrief UK · Mon, 03 Aug 2026 15:33:00 GMTAnthropic says three Claude models reached real-world systems during cyber tests - axios.comaxios.com · Thu, 30 Jul 2026 07:00:00 GMTOpenAI's Security Test Causes Chaos, AI Agent Breaks Hugging Face - VOI.IDVOI.ID · Thu, 30 Jul 2026 04:53:45 GMT