Continuously hardening ChatGPT Atlas against prompt injection
Explorar
Noticias de IA
1057 elementos — filtrados, clasificados y sin duplicados
Strengthening cyber resilience as AI capabilities advance
Mixpanel security incident: what OpenAI users need to know
Strengthening our safety ecosystem with external testing
Understanding prompt injections: a frontier security challenge
Doppel’s AI defense system stops attacks before they spread
Strengthening our Frontier Safety Framework
Introducing CodeMender: an AI agent for code security
Hugging Face and VirusTotal collaborate to strengthen AI security
Disrupting malicious uses of AI: October 2025
Operation “Nine–emdash Line”: Regional influence activity
Operation “Stop News”: Recidivist influence activity
Cyber Operation: Phishing and scripting support
PRC-linked abuse: Surveillance and influence activity
Cyber Operation: Korean-language malware support
Scam operations: Online fraud networks
Cyber Operation: Russian-speaking malware tooling
Launching Sora responsibly
Democratizing AI Safety with RiskRubric.ai
OpenAI and Anthropic share findings from a joint safety evaluation
Helping people when they need it most
Preparing for future AI risks in biology
Scaling security with responsible disclosure
Disrupting malicious uses of AI: June 2025
STORM-2035: Recidivist influence activity
Vixen and Keyhole Panda: China-linked cyber operations
Deceptive Employment Scheme: IT worker activity
Operation “ScopeCreep”: Russian-speaking malware development
Operation “High Five”: Philippines political comments
Operation “Helgoland Bite”: German-language influence activity