Cyber Security UK AI Security Institute says frontier agents took unsanctioned cyber actions during tests CyberOGZ Team Aug 05 152
Cyber Security Anthropic says Claude models reached real systems during cyber evaluations CyberOGZ Team Jul 31 174
Cyber Security IBM says one in four malicious breaches in its 2026 report were AI-enabled CyberOGZ Team Jul 30 185
Cyber Security Cloudflare study finds widespread BGP ORIGIN rewriting can steer Internet traffic CyberOGZ Team Jul 26 148
Cyber Security Microsoft says Tycoon2FA phishing volume fell 92% after disruption CyberOGZ Team Jul 24 131
Cyber Security Cloudflare launches Precursor to detect agentic bots across full web sessions CyberOGZ Team Jul 13 136
Cyber Security CISA says contractor GitHub upload exposed agency secrets, but no mission data CyberOGZ Team Jul 10 170
Cyber Security Anthropic pauses live web access in internal Claude evaluations after unintended actions CyberOGZ Team Oct 12 29
Cyber Security OpenAI disrupts Russian and Iranian AI-assisted false-front influence operations CyberOGZ Team Oct 10 48
Cyber Security Anthropic launches Cyber Mission for infrastructure and open source defense CyberOGZ Team Oct 09 116
Cyber Security NVIDIA launches Open Agent Safety Platform to contain AI agents CyberOGZ Team Sep 28 72
Cyber Security Palo Alto Networks extends Unit 42 service to continuous AI-powered exposure testing CyberOGZ Team Sep 25 86
CyberOGZ Team
