56 citations · 144 across the 48 of their papers we have counts for
53 papers
Benchmarking Jailbreak Guardrails for Embodied Agents
Xunguang Wang, Qingyue Wang, Yuguang Zhou +3
Embodied agents powered by large language models and vision-language models are increasingly deployed in physical environments, but jailbreak attacks can induce these agents to per…
Decompiling Quantum Assembly into Structured Programs
Pingchuan Ma, Zhantong Xue, Zongjie Li +6
Quantum compilers translate programs into native gates, insert SWAP gates to route interactions onto a device, and optimize the result. The output is quantum assembly, a flat gate…
Reassembling Distributed Risk: Trajectory-Conditioned Action Generation for Multi-Turn Agent Safety
Yanbo Dai, Zhenlan Ji, Zongjie Li +1
Tool-using LLM agents extend security risks beyond generated text to actions that affect external systems. Under multi-turn decomposition attacks, a harmful objective can be distri…
Uncovering and Understanding Hidden Dependencies in the LLM API Reseller Ecosystem via Prefix-Cache Side Channels
Zimo Ji, Xin Wei, Congying Xu +5
LLM API resellers have become an important access layer to modern LLM services. However, multi-level resale creates an opaque supply chain: a user's request may traverse undisclose…
AutoSpec: Safety Rule Evolution for LLM Agents via Inductive Logic Programming
Pingchuan Ma, Zhaoyu Wang, Zimo Ji +5
Large language model (LLM) agents increasingly automate complex tasks by integrating language models with external tools and environments. However, their autonomy poses significant…
Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware
Zimo Ji, Congying Xu, Zongjie Li +4
LLM coding agents increasingly rely on third-party agent skills from public marketplaces, which execute with the agent's privileges and create a software supply-chain attack surfac…
Coding Agents Are Guessing: Measuring Action-Boundary Violations in Underspecified DevOps Instructions
Zimo Ji, Zekai Zhang, Congying Xu +4
LLM coding agents are increasingly deployed to act autonomously on real production infrastructure. They execute shell commands, modify repositories, and call operational APIs. Howe…
Unlocking Proactivity in Task-Oriented Dialogue
Azure Zhang, Ning Gao, Yuqin Dai +7
Proactive task-oriented dialogue (TOD), such as outbound sales, demands a persuasive agent that actively probes the user's concerns and steers the conversation toward acceptance wi…
Measuring the Permission Gate: A Stress-Test Evaluation of Claude Code's Auto Mode
Zimo Ji, Zongjie Li, Pingchuan Ma +3
Claude Code's auto mode is the first deployed permission system for AI coding agents, using a two-stage transcript classifier to gate dangerous tool calls. Anthropic reports a 0.4%…
Cascaded Code Editing: Large-Small Model Collaboration for Effective and Efficient Code Editing
Chaozheng Wang, Zezhou Yang, Shuzheng Gao +7
Code editing constitutes a fundamental practice in software development, wherein developers modify existing codebases according to natural language requirements. Accurate code edit…
WARBENCH: A Comprehensive Benchmark for Evaluating LLMs in Military Decision-Making
Zongjie Li, Chaozheng Wang, Yuchong Xie +2
Large Language Models are increasingly being considered for deployment in safety-critical military applications. However, current benchmarks suffer from structural blindspots that…
SkillReducer: Optimizing LLM Agent Skills for Token Efficiency
Yudong Gao, Zongjie Li, Yuanyuan Yuan +3
LLM-based coding agents rely on \emph{skills}, pre-packaged instruction sets that extend agent capabilities, yet every token of skill content injected into the context window incur…
Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models
Xunguang Wang, Yuguang Zhou, Qingyue Wang +5
Large language models increasingly rely on explicit chain-of-thought reasoning to solve complex tasks, yet the safety of the reasoning process itself remains largely unaddressed. E…
On Protecting Agentic Systems' Intellectual Property via Watermarking
Liwen Wang, Zongjie Li, Yuchong Xie +4
The evolution of Large Language Models (LLMs) into agentic systems that perform autonomous reasoning and tool use has created significant intellectual property (IP) value. We demon…
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…
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…
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…
QueryIPI: Query-agnostic Indirect Prompt Injection on Coding Agents
Yuchong Xie, Zesen Liu, Mingyu Luo +7
Modern coding agents integrated into IDEs orchestrate powerful tools and high-privilege system access, creating a high-stakes attack surface. Prior work on Indirect Prompt Injectio…
JSProtect: A Scalable Obfuscation Framework for Mini-Games in WeChat
Zhihao Li, Chaozheng Wang, Zongjie Li +12
The WeChat mini-game ecosystem faces rampant intellectual property theft to other platforms via secondary development, yet existing JavaScript obfuscation tools are ill-equipped fo…
A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users
Nishant Balepur, Matthew Shu, Yoo Yeon Sung +5
To assist users in complex tasks, LLMs generate plans: step-by-step instructions towards a goal. While alignment methods aim to ensure LLM plans are helpful, they train (RLHF) or e…
Empirical Study of Code Large Language Models for Binary Security Patch Detection
Qingyuan Li, Binchang Li, Cuiyun Gao +2
Security patch detection (SPD) is crucial for maintaining software security, as unpatched vulnerabilities can lead to severe security risks. In recent years, numerous learning-base…
Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment
Yuchong Xie, Mingyu Luo, Zesen Liu +7
Coding agents powered by large language models are becoming central modules of modern IDEs, helping users perform complex tasks by invoking tools. While powerful, tool invocation o…
JSidentify-V2: Leveraging Dynamic Memory Fingerprinting for Mini-Game Plagiarism Detection
Zhihao Li, Chaozheng Wang, Zongjie Li +9
The explosive growth of mini-game platforms has led to widespread code plagiarism, where malicious users access popular games' source code and republish them with modifications. Wh…
DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version)
Yanbo Dai, Zhenlan Ji, Zongjie Li +2
Retrieval-Augmented Generation (RAG) has become a standard approach for improving the reliability of large language models (LLMs). Prior work demonstrates the vulnerability of RAG…