Yingjiu Li

发表论文 4 篇 · 总被引 120 次 · h-index 3

代表论文

• SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner (2024 · USENIX Security Symposium · 被引 79)
• MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols (2025 · arXiv.org · 被引 57)
• Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control Framework (2026 · arXiv.org · 被引 50)
• Rethinking and Exploring String-Based Malware Family Classification in the Era of LLMs and RAG (2025 · arXiv.org · 被引 1)