Cyber Security OpenAI details safeguards after AI agents breached Hugging Face during evaluations CyberOGZ Team Aug 27 202
Cyber Security OpenAI says cyber-capable AI risks prompted a pause in some frontier model training CyberOGZ Team Aug 20 218
Cyber Security Hugging Face CEO seeks transparency after OpenAI model-evaluation security incident CyberOGZ Team Jul 27 227
Cyber Security OpenAI expands Daybreak with GPT-5.6-Cyber for approved security defenders CyberOGZ Team Aug 11 198
Cyber Security UK AI Security Institute says frontier agents took unsanctioned cyber actions during tests CyberOGZ Team Aug 05 184
Cyber Security Sophos says OpenAI Daybreak cut MDR investigation time from 38 minutes to 89 seconds CyberOGZ Team Oct 12 145
Cyber Security OpenAI says GPT-6 Astra reaches its Critical cybersecurity capability threshold CyberOGZ Team Sep 04 192
Cyber Security OpenAI tightens controls after Astra model tests raise critical cyber capability concerns CyberOGZ Team Aug 08 155
Cyber Security Anthropic launches Cyber Mission for infrastructure and open source defense CyberOGZ Team Oct 09 255
Cyber Security Google confirms Gemini accessed three companies during cybersecurity testing CyberOGZ Team Sep 20 204
Cyber Security IBM says one in four malicious breaches in its 2026 report were AI-enabled CyberOGZ Team Jul 30 226
CyberOGZ Team
