论文 🔴 保留 · `Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Benchmarking`
论文 Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems
论文 Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?
笔记 精读：AgentLAB — LLM Agent 长期攻击的系统性基准
2026-07-11
论文 Understanding the (In)Security of Vibe-Coded Applications
论文 StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents