collaborators

7 papers

cs.CR2026

LoopTrap: Termination Poisoning Attacks on LLM Agents

Huiyu Xu, Zhibo Wang, Wenhui Zhang +4

Modern LLM agents solve complex tasks by operating in iterative execution loops, where they repeatedly reason, act, and self-evaluate progress to determine when a task is complete.…

eess.AS2026

Streaming Speech Recognition with Decoder-Only Large Language Models and Latency Optimization

Genshun Wan, Wenhui Zhang, Jing-Xuan Zhang +3

Recent advances have demonstrated the potential of decoderonly large language models (LLMs) for automatic speech recognition (ASR). However, enabling streaming recognition within t…

cs.CR2026

RerouteGuard: Understanding and Mitigating Adversarial Risks for LLM Routing

Wenhui Zhang, Huiyu Xu, Zhibo Wang +4

Recent advancements in multi-model AI systems have leveraged LLM routers to reduce computational cost while maintaining response quality by assigning queries to the most appropriat…

cs.CR2025

Interpretable LLM Guardrails via Sparse Representation Steering

Zeqing He, Zhibo Wang, Huiyu Xu +3

Large language models (LLMs) exhibit impressive capabilities in generation tasks but are prone to producing harmful, misleading, or biased content, posing significant ethical and s…

cs.CR2025

ZTaint-Havoc: From Havoc Mode to Zero-Execution Fuzzing-Driven Taint Inference

Yuchong Xie, Wenhui Zhang, Dongdong She

Fuzzing is a widely used technique for discovering software vulnerabilities, but identifying hot bytes that influence program behavior remains challenging. Traditional taint analys…

cs.SE2025

CXXCrafter: An LLM-Based Agent for Automated C/C++ Open Source Software Building

Zhengmin Yu, Yuan Zhang, Ming Wen +3

Project building is pivotal to support various program analysis tasks, such as generating intermediate rep- resentation code for static analysis and preparing binary code for vulne…