collaborators

9 papers

cs.CR2026

Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control Framework

Zimo Ji, Daoyuan Wu, Wenyuan Jiang +5

Large Language Model (LLM)-based agent systems are increasingly deployed for complex real-world tasks but remain vulnerable to natural language-based attacks that exploit over-priv…

cs.CR2025

Taxonomy, Evaluation and Exploitation of IPI-Centric LLM Agent Defense Frameworks

Zimo Ji, Xunguang Wang, Zongjie Li +6

Large Language Model (LLM)-based agents with function-calling capabilities are increasingly deployed, but remain vulnerable to Indirect Prompt Injection (IPI) attacks that hijack t…

cs.CR2025

SEAL: Subspace-Anchored Watermarks for LLM Ownership

Yanbo Dai, Zongjie Li, Zhenlan Ji +1

Large language models (LLMs) have achieved remarkable success across a wide range of natural language processing tasks, demonstrating human-level performance in text generation, re…

cs.SE2025

Evaluating LLMs on Sequential API Call Through Automated Test Generation

Yuheng Huang, Jiayang Song, Da Song +4

By integrating tools from external APIs, Large Language Models (LLMs) have expanded their promising capabilities in a diverse spectrum of complex real-world tasks. However, testing…

cs.AI2025

Measuring and Augmenting Large Language Models for Solving Capture-the-Flag Challenges

Zimo Ji, Daoyuan Wu, Wenyuan Jiang +3

Capture-the-Flag (CTF) competitions are crucial for cybersecurity education and training. As large language models (LLMs) evolve, there is increasing interest in their ability to a…

cs.CR2025

Differentiation-Based Extraction of Proprietary Data from Fine-Tuned LLMs

Zongjie Li, Daoyuan Wu, Shuai Wang +1

The increasing demand for domain-specific and human-aligned Large Language Models (LLMs) has led to the widespread adoption of Supervised Fine-Tuning (SFT) techniques. SFT datasets…