27 citations · 70 across the 44 of their papers we have counts for
46 papers
Mobile App Analysis in the New Era: Challenges and the Road Ahead
Jiale Wu, Tianming Liu, Yanjie Zhao +1
Mobile applications (apps) have grown into complex, multi-platform systems that support diverse services and operate within varying regulatory and distribution contexts. Traditiona…
MalTotal: Cost-Effective and Language-Agnostic Malicious Code Poisoning Detection for Millions of Repositories
Jian Zhao, Shenao Wang, Qingyang Wu +3
The widespread adoption of open source software (OSS) has introduced significant security risks, with malicious code poisoning attacks increasingly targeting public package registr…
LogicHunter: Testing LLM Agent Frameworks with an Agentic Oracle
Minghui Long, Yanjie Zhao, Haoyu Wang
Large Language Model (LLM) agent frameworks such as LangChain, LlamaIndex, and CrewAI have become critical infrastructure powering production AI systems, yet they remain severely u…
Neuro-Symbolic Reasoning for Vulnerability Detection
Yanjie Zhao, Hongjie Chen, Li Lu +3
Ask a large language model (LLM) whether a pointer dereference is safe, and it can often produce a plausible justification for ``yes''. The difficulty is that a fluent justificatio…
When Agents Do Not Stop: Uncovering Infinite Agentic Loops in LLM Agents
Xinyi Hou, Shenao Wang, Yanjie Zhao +1
LLM agents increasingly rely on iterative execution to solve tasks through planning, tool use, state updates, and agent collaboration. While this design enables flexible automation…
AgentFlow: Building Agent Dependency Graphs for Static Analysis of Agent Programs
Shenao Wang, Xinyi Hou, Yanjie Zhao +2
LLM agents are increasingly developed as source-code applications built on agent frameworks. These agent programs combine conventional host-language code with framework-defined sem…
Acoda: Adversarial Code Obfuscation for Defending against LLM-based Analysis
Hongzhou Rao, Zikan Dong, Yanjie Zhao +2
With the widespread adoption of Large Language Models (LLMs) in software engineering (SE) tasks such as code understanding, debugging, and vulnerability detection, their powerful s…
Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks
Qiang Ke, Yanjie Zhao, Hongjin Leng +2
While Retrieval-Augmented Generation (RAG) is increasingly adopted to ground Large Language Models (LLMs) in software artifacts, the optimal configuration of its components remains…
Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solvers
Haoyu Wang, Yuliang Song, Tao Li +5
Large Language Models (LLMs) struggle to solve complex combinatorial problems through direct reasoning, so recent neuro-symbolic systems increasingly use them to synthesize executa…
Unsafe by Flow: Uncovering Bidirectional Data-Flow Risks in MCP Ecosystem
Xinyi Hou, Yanjie Zhao, Haoyu Wang
Model Context Protocol (MCP) have quickly become the interface layer between LLM agents and external tools, yet they also introduce unsafe data flows that existing analyzers handle…
Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions
Shenao Wang, Xinyi Hou, Zhao Liu +5
GitHub Actions is increasingly used to deploy LLM-based agents for repository-centric tasks such as issue triage, pull-request review, code modification, and release assistance. Th…
CommitSuite: A Comprehensive Benchmark for Commit Classification and Message Generation
Zirui Wan, Zhaonan Wu, Xinyi Hou +3
High-quality commit messages are critical for maintaining software projects, yet ensuring their consistency and informativeness remains a practical challenge. While the Conventiona…
MalSkills: Detecting Malicious Skills in the Agentic Supply Chain via Neuro-symbolic Reasoning
Shenao Wang, Junjie He, Yanjie Zhao +3
Skills are increasingly used to extend LLM agents by packaging prompts, code, and configurations into reusable modules. As public registries and marketplaces expand, they form an e…
Evaluating and Enhancing the Vulnerability Reasoning Capabilities of Large Language Models
Li Lu, Yanjie Zhao, Hongzhou Rao +2
Large Language Models (LLMs) have demonstrated remarkable proficiency in vulnerability detection. However, a critical reliability gap persists: models frequently yield correct dete…
Agent-Based Software Artifact Evaluation
Zhaonan Wu, Yanjie Zhao, Zhenpeng Chen +2
Artifact Evaluation (AE) has become a standard mechanism for linking software engineering papers to their supporting artifacts, but growing submission volume makes purely manual AE…
SMCP: Secure Model Context Protocol
Xinyi Hou, Shenao Wang, Yifan Zhang +4
Agentic AI systems built around large language models (LLMs) are moving away from closed, single-model frameworks and toward open ecosystems that connect a variety of agents, exter…
YASA: Scalable Multi-Language Taint Analysis on the Unified AST at Ant Group
Yayi Wang, Shenao Wang, Jian Zhao +7
Modern enterprises increasingly adopt diverse technology stacks with various programming languages, posing significant challenges for static application security testing (SAST). Ex…
Demystifying Cookie Sharing Risks in WebView-based Mobile App-in-app Ecosystems
Miao Zhang, Shenao Wang, Guilin Zheng +2
Mini-programs, an emerging mobile application paradigm within super-apps, offer a seamless and installation-free experience. However, the adoption of the web-view component has dis…
LaQual: An Automated Framework for LLM App Quality Evaluation
Yan Wang, Xinyi Hou, Junjun Si +3
Representing a new paradigm in software distribution, LLM app stores are rapidly emerging, offering users diverse choices for content generation, coding assistance, education, and…
Gradient-Based Model Fingerprinting for LLM Similarity Detection and Family Classification
Zehao Wu, Yanjie Zhao, Haoyu Wang
As Large Language Models (LLMs) become integral software components in modern applications, unauthorized model derivations through fine-tuning, merging, and redistribution have eme…
Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead
Hongzhou Rao, Yanjie Zhao, Xinyi Hou +2
The rapid advancement of large language models (LLMs) has redefined artificial intelligence (AI), pushing the boundaries of AI research and enabling unbounded possibilities for bot…
CodeMorph: Mitigating Data Leakage in Large Language Model Assessment
Hongzhou Rao, Yanjie Zhao, Wenjie Zhu +3
Concerns about benchmark leakage in large language models for code (Code LLMs) have raised issues of data contamination and inflated evaluation metrics. The diversity and inaccessi…
Toward Understanding Bugs in Vector Database Management Systems
Yinglin Xie, Xinyi Hou, Yanjie Zhao +3
Vector database management systems (VDBMSs) play a crucial role in facilitating semantic similarity searches over high-dimensional embeddings from diverse data sources. While VDBMS…
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents
Liangxuan Wu, Chao Wang, Tianming Liu +2
The growing adoption of large language models (LLMs) has led to a new paradigm in mobile computing--LLM-powered mobile AI agents--capable of decomposing and automating complex task…