33 citations · 127 across the 30 of their papers we have counts for
32 papers
FlowScout: From Execution Feedback to Reliable Tool-Using Agent Workflows
Shuo Hao, You Lu, Bihuan Chen +1
Agentic workflows have become an important abstraction for building reliable LLM-based automation systems by organizing large language models (LLMs), tools, and control logic into…
DOCSCHISEL: Adaptive Tool Documentation Optimization Framework for LLM Agents
You Lu, Kun Zhang, Bihuan Chen +1
Large language models (LLMs) increasingly rely on external tools to accomplish complex real-world tasks, making tool documentation a critical grounding resource for LLM agents. Exi…
SkillSentry: Reliable Skill Execution for LLM Agents via Runtime Assurance
You Lu, Xinyu Huang, Bihuan Chen +1
LLM agents are increasingly equipped with skills to perform complex tasks through multi-step reasoning and tool use. Although skills provide reusable procedural knowledge, agents m…
ProfMalPlus: Agent-Coordinated Detection of Malicious NPM Packages via Static-Dynamic Analysis Synergy
Yiheng Huang, Zhijia Zhao, Bihuan Chen +6
Open source software is vulnerable to supply-chain attacks through transitive dependencies, especially malicious code injected into NPM packages. Existing detectors often inadequat…
From Component Manipulation to System Compromise: Understanding and Detecting Malicious MCP Servers
Yiheng Huang, Zhijia Zhao, Bihuan Chen +5
The model context protocol (MCP) standardizes how LLMs connect to external tools and data sources, enabling faster integration but introducing new attack vectors. Despite the growi…
Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code
Kaifeng He, Xiaojun Zhang, Peiliang Cai +7
Large language models (LLMs) frequently generate defective code, ranging from logical bugs to security vulnerabilities. Training-data quality is one contributor to these outcomes a…
VulWeaver: Weaving Broken Semantics for Grounded Vulnerability Detection
Yiheng Cao, Yihao Chen, Xin Hu +9
Detecting vulnerabilities in source code remains critical yet challenging, as conventional static analysis tools construct inaccurate program representations, while existing LLM-ba…
AutoMerge: Search-Based Model Merging Framework for Effective Model Reuse
You Lu, Jiyang Zhang, Bihuan Chen +3
Software reuse has long been recognized as a critical and widely studied topic in software engineering, offering substantial benefits in reducing development costs, improving softw…
ExpertAD: Enhancing Autonomous Driving Systems with Mixture of Experts
Haowen Jiang, Xinyu Huang, You Lu +6
Recent advancements in end-to-end autonomous driving systems (ADSs) underscore their potential for perception and planning capabilities. However, challenges remain. Complex driving…
Argus: Resilience-Oriented Safety Assurance Framework for End-to-End ADSs
Dingji Wang, You Lu, Bihuan Chen +4
End-to-end autonomous driving systems (ADSs), with their strong capabilities in environmental perception and generalizable driving decisions, are attracting growing attention from…
TigAug: Data Augmentation for Testing Traffic Light Detection in Autonomous Driving Systems
You Lu, Dingji Wang, Kaifeng Huang +2
Autonomous vehicle technology has been developed in the last decades with recent advances in sensing and computing technology. There is an urgent need to ensure the reliability and…
A Survey of Fuzzing Open-Source Operating Systems
Kun Hu, Qicai Chen, Wenzhuo Zhang +7
Vulnerabilities in open-source operating systems (OSs) pose substantial security risks to software systems, making their detection crucial. While fuzzing has been an effective vuln…
RoadGen: Generating Road Scenarios for Autonomous Vehicle Testing
Fan Yang, You Lu, Bihuan Chen +2
With the rapid development of autonomous vehicles, there is an increasing demand for scenario-based testing to simulate diverse driving scenarios. However, as the base of any drivi…
DynNPC: Finding More Violations Induced by ADS in Simulation Testing through Dynamic NPC Behavior Generation
You Lu, Yifan Tian, Dingji Wang +2
Recently, a number of simulation testing approaches have been proposed to generate diverse driving scenarios for autonomous driving systems (ADSs) testing. However, the behaviors o…
Lifting the Veil on Composition, Risks, and Mitigations of the Large Language Model Supply Chain
Kaifeng Huang, Bihuan Chen, You Lu +7
Large language models (LLMs) have sparked significant impact with regard to both intelligence and productivity. Numerous enterprises have integrated LLMs into their applications to…
Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG
Xueying Du, Geng Zheng, Kaixin Wang +9
Although LLMs have shown promising potential in vulnerability detection, this study reveals their limitations in distinguishing between vulnerable and similar-but-benign patched co…
A general approach to enhance the survivability of backdoor attacks by decision path coupling
Yufei Zhao, Dingji Wang, Bihuan Chen +2
Backdoor attacks have been one of the emerging security threats to deep neural networks (DNNs), leading to serious consequences. One of the mainstream backdoor defenses is model re…
Detecting and Fixing Violations of Modification Terms in Open Source Licenses during Forking
Kaifeng Huang, Yingfeng Xia, Bihuan Chen +3
Open source software brings benefit to software community, but also introduces legal risks caused by license violations, which result in serious consequences such as lawsuits and f…
Exploring the Potential of ChatGPT in Automated Code Refinement: An Empirical Study
Qi Guo, Junming Cao, Xiaofei Xie +4
Code review is an essential activity for ensuring the quality and maintainability of software projects. However, it is a time-consuming and often error-prone task that can signific…
Killing Two Birds with One Stone: Malicious Package Detection in NPM and PyPI using a Single Model of Malicious Behavior Sequence
Junan Zhang, Kaifeng Huang, Yiheng Huang +4
Open-source software (OSS) supply chain enlarges the attack surface, which makes package registries attractive targets for attacks. Recently, package registries NPM and PyPI have b…
Scalable and Precise Application-Centered Call Graph Construction for Python
Kaifeng Huang, Yixuan Yan, Bihuan Chen +2
Call graph construction is the foundation of inter-procedural static analysis. PYCG is the state-of-the-art approach for constructing call graphs for Python programs. Unfortunately…
Understanding the Complexity and Its Impact on Testing in ML-Enabled Systems
Junming Cao, Bihuan Chen, Longjie Hu +3
Machine learning (ML) enabled systems are emerging with recent breakthroughs in ML. A model-centric view is widely taken by the literature to focus only on the analysis of ML model…
Has My Release Disobeyed Semantic Versioning? Static Detection Based on Semantic Differencing
Lyuye Zhang, Chengwei Liu, Zhengzi Xu +4
To enhance the compatibility in the version control of Java Third-party Libraries (TPLs), Maven adopts Semantic Versioning (SemVer) to standardize the underlying meaning of version…
Demystifying Dependency Bugs in Deep Learning Stack
Kaifeng Huang, Bihuan Chen, Susheng Wu +3
Deep learning (DL) applications, built upon a heterogeneous and complex DL stack (e.g., Nvidia GPU, Linux, CUDA driver, Python runtime, and TensorFlow), are subject to software and…