Zongjie Li
发表论文 70 篇 · 总被引 1137 次 · h-index 21
代表论文
- Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control Framework (2026 · arXiv.org · 被引 50)
- DecLLM: LLM-Augmented Recompilable Decompilation for Enabling Programmatic Use of Decompiled Code (2025 · Proc. ACM Softw. Eng. · 被引 41)
- SkillReducer: Optimizing LLM Agent Skills for Token Efficiency (2026 · arXiv.org · 被引 28)
- Sok: Evaluating Jailbreak Guardrails for Large Language Models (2025 · IEEE Symposium on Security and Privacy · 被引 25)
- Differentiation-Based Extraction of Proprietary Data from Fine-Tuned LLMs (2025 · Conference on Computer and Communications Security · 被引 14)
- Measuring the Permission Gate: A Stress-Test Evaluation of Claude Code's Auto Mode (2026 · arXiv.org · 被引 9)