15 papers
When Verified Source Becomes Attack Input: Defending Smart Contracts Against LLM-Based Vulnerability Scanning
Mingyuan Huang, Zimo Ji, Yifan Mo +1
Smart contracts are financial programs deployed on blockchains to manage digital assets. To build trust with users and investors, smart contract projects typically publish their so…
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…
Position: Multi-Agent Systems Should Prioritize Concurrency Control
Xin Yang, Letian Li, Zimo Ji +2
LLM-based multi-agent systems (MAS) promise scalable collaboration, yet adding agents often reduces reliability. This position paper argues that many MAS failures are fundamentally…
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…
PathMark: Protecting Intellectual Property of Mixture-of-Expert LLMs via Path Watermarks
Yudong Gao, Qingyue Wang, Yuanyuan Yuan +4
Mixture-of-Experts (MoE) large language models represent high-value intellectual property, yet existing watermarking schemes designed for dense models fail on MoE architectures due…
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…
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%…
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…
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…
CryptoScope: Utilizing Large Language Models for Automated Cryptographic Logic Vulnerability Detection
Zhihao Li, Zimo Ji, Tao Zheng +2
Cryptographic algorithms are fundamental to modern security, yet their implementations frequently harbor subtle logic flaws that are hard to detect. We introduce CryptoScope, a nov…
INTEGRALBENCH: Benchmarking LLMs with Definite Integral Problems
Bintao Tang, Xin Yang, Yuhao Wang +3
We present INTEGRALBENCH, a focused benchmark designed to evaluate Large Language Model (LLM) performance on definite integral problems. INTEGRALBENCH provides both symbolic and nu…
Towards Provable (In)Secure Model Weight Release Schemes
Xin Yang, Bintao Tang, Yuhao Wang +3
Recent secure weight release schemes claim to enable open-source model distribution while protecting model ownership and preventing misuse. However, these approaches lack rigorous…
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…