AI News · #security · anthropic-research

Anthropic Research · 2026-07-08 제목번역

에이전틱 오정렬: LLM이 내부자 위협이 될 수 있는 방식

Agentic misalignment: How LLMs could be insider threats

#ai-safety #agentic-misalignment #security #llms #insider-threats

Anthropic Research · 2026-06-26 제목번역

Reverse engineering Claude's CVE-2026-2796 exploit

#claude #security #reverse-engineering #vulnerability #exploit #cve

Anthropic Research · 2026-06-24 제목번역

Developing Nuclear Safeguards for AI

#ai-safety #security #nuclear-safeguards #risk-mitigation #defense

Anthropic Research · 2026-06-17 제목번역

AI agents find smart contract exploits

#ai-agents #security #smart-contracts #exploit-detection #blockchain

Anthropic Research · 2026-06-17 제목번역

Building AI for cyber defenders

#threat-detection #ai-defense #security #cybersecurity #defenders