Research Profile
I am a Postdoctoral Researcher at the State Key Laboratory of Intelligent Game, Institute of Software, Chinese Academy of Sciences (ISCAS). My research focuses on crowd-based knowledge extraction and analysis, software security threat analysis, vulnerability identification and automated repair, the security of LLM tool-learning systems, and security risks in AIGC-generated multimodal content.
Education and Appointments
- Since 2025: Postdoctoral Researcher, Institute of Software, Chinese Academy of Sciences, advised by Prof. Qing Wang
- Since 2025: Self-Employed Researcher, SIGMIR
- 2019-2025: Ph.D. in Software Engineering, Institute of Software, Chinese Academy of Sciences, advised by Prof. Qing Wang
- 2015-2019: B.S. in Software Engineering, Xiamen University
Research Interests
- Crowd-based knowledge extraction and analysis
- Software security threat analysis, vulnerability detection, and automated repair
- Security of LLM tool-learning systems
- Security of AIGC-generated multimodal content
First-Authored Publications
- Ziyou Jiang, Mingyang Li, Junjie Wang, Yuekai Huang, Jie Huang, Zhiyuan Chang, Zhaoyang Li, Qing Wang. All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction. ACL 2026 (Main, Top 15%). [ArXiv]
- Ziyou Jiang, Mingyang Li, Guowei Yang, Lin Shi, Junjie Wang, Qing Wang. VulRTex: A Reasoning-Guided Approach to Identify Vulnerabilities from Rich-Text Issue Report. TOSEM 2026. [ArXiv] [Paper]
- Ziyou Jiang, Mingyang Li, Guowei Yang, Junjie Wang, Yuekai Huang, Zhiyuan Chang, Qing Wang. Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System. ACL 2025: 13677-13693. ACL 2025 SAC Highlight Award. [Paper]
- Ziyou Jiang, Lin Shi, Guowei Yang, Qing Wang. PatUntrack: Automated Generating Patch Examples for Issue Reports without Tracked Insecure Code. ASE 2024: 1-13. [Paper]
- Ziyou Jiang, Lin Shi, Guowei Yang, Qing Wang. SCPatcher: Mining Crowd Security Discussions to Enrich Secure Coding Practices. ASE 2023: 358-370. [Paper]
- Ziyou Jiang, Lin Shi, Celia Chen, Fangwen Mu, Yumin Zhang, Qing Wang. MuiDial: Improving Dialogue Disentanglement with Intent-Based Mutual Learning. IJCAI 2022: 4164-4170. [Paper]
- Lin Shi, Ziyou Jiang (equal contribution), Ye Yang, Xiao Chen, Yumin Zhang, Fangwen Mu, Hanzhi Jiang, Qing Wang. ISPY: Automatic Issue-Solution Pair Extraction from Community Live Chats. ASE 2021: 142-154. ASE 2021 ACM Distinguished Paper Award. [Paper]
- Ziyou Jiang, Lin Shi, Celia Chen, Jun Hu, Qing Wang. Dialogue Disentanglement in Software Engineering: How Far Are We? IJCAI 2021: 3822-3828. [Paper]
Selected Co-Authored Publications
- Jie Huang, Junjie Wang, Xin Liao, Ziyou Jiang, Wenshuo Wang, Shoubin Li, Qing Wang. Generative Text-to-Image Retrieval via Hierarchical Identifiers and Semantic Internalization. ACL 2026.
- Jie Huang, Xin Liao, Junjie Wang, Mingyang Li, Wenshuo Wang, Ziyou Jiang, Shoubin Li, Qing Wang. SAGE: Synergistic Adaptive Gating of Experts for Hateful Video Detection. ACL 2026.
- Zhiyuan Chang, Mingyang Li, Yuekai Huang, Ziyou Jiang, Xiaojun Jia, Qian Xiong, Junjie Wang, Zhaoyang Li, Qing Wang. Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning. ACL 2026.
- Yujia Zheng, Tianhao Li, Haotian Huang, Tianyu Zeng, Jingyu Lu, Chuangxin Chu, Yuekai Huang, Ziyou Jiang, Qian Xiong, Yuyao Ge, Mingyang Li. Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in LLMs. EACL 2026. Evaluation and Model Insight Award. [ArXiv]
- Qian Xiong, Yuekai Huang, Ziyou Jiang, Zhiyuan Chang, Yu Zheng, Tianhao Li, Mingyang Li. Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems. EMNLP 2025. [ArXiv] [Paper]
- Zhiyuan Chang, Mingyang Li, Xiaojun Jia, Junjie Wang, Yuekai Huang, Ziyou Jiang, Yang Liu, Qing Wang. One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems. EMNLP 2025. [ArXiv] [Paper]
- Lin Shi, Xiao Chen, Ye Yang, Hanzhi Jiang, Ziyou Jiang, Nan Niu, Qing Wang. A First Look at Developers’ Live Chat on Gitter. ESEC/SIGSOFT FSE 2021: 391-403. [Paper]
- Lin Shi, Fangwen Mu, Yumin Zhang, Ye Yang, Junjie Chen, Xiao Chen, Hanzhi Jiang, Ziyou Jiang, Qing Wang. BugListener: Identifying and Synthesizing Bug Reports from Collaborative Live Chats. ICSE 2022: 299-311. [Paper]
Academic Service
- Invited reviewer: IEEE Transactions on Software Engineering (TSE 2024), IEEE Transactions on Big Data (TBD 2024), ACM Transactions on Software Engineering and Methodology (TOSEM)
- Conference service: AAAI 2025, ACL 2026, ASE, ICSE, and ESEC/FSE
Projects
- 2026: Postdoctoral Fellowship Program and China Postdoctoral Science Foundation (C)
- 2026: China Postdoctoral Science Foundation
- 2025: China Postdoctoral Science Foundation, International Academic Exchange Program
- 2024: National Key Research and Development Program of China, “Security Risks in AIGC-Generated Multimodal Content,” Project Secretary and Core R&D Personnel
- 2021: Huawei Poplar Forest Fund, Core R&D Personnel
Honors and Awards
- 2026: Evaluation and Model Insight Award, EACL 2026
- 2025: Third Prize, ChinaSoft 2025 National Prototype System Competition (SEAutoCMD)
- 2025: Excellent Poster Award, ISCAS Academic Annual Conference
- 2025: ACL 2025 SAC Highlight Award
- 2025: Outstanding Scholarship for President of the Chinese Academy of Sciences
- 2024: Three Good Students, University of Chinese Academy of Sciences
- 2022: Three Good Students, University of Chinese Academy of Sciences
- 2021: Representative Accomplishments, ISCAS Academic Annual Conference
- 2021: ACM Distinguished Paper Award, ASE 2021
- 2018: Hua-Bin QIU Scholarship, Xiamen University Anniversary Celebration
- 2017: National Third Prize, Chinese University Students Service Outsourcing Innovation and Entrepreneurship Competition
- 2017: Fujian Province Second Prize, Chinese University Students Mathematical Modeling Competition
- 2017: Academic First-Class Scholarship, Xiamen University
- 2017: Academic Innovation Scholarship, Xiamen University
Selected Talks
- 2025: ACL 2025, poster presentation of “Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System”
- 2024: Graduate Academic Forum of the University of Chinese Academy of Sciences, poster presentation
- 2024: ASE 2024, presentation of “PatUntrack: Automated Generating Patch Examples for Issue Reports without Tracked Insecure Code”
- 2023: ASE 2023, presentation of “SCPatcher: Mining Crowd Security Discussions to Enrich Secure Coding Practices”
- 2021: ChinaSoft Forum of Top Conference and Journal, online presentation
Latest News
- Four papers from our group were accepted to ACL 2026, supported by the National Key Research and Development Program of China.
- Our work on vulnerability identification from rich-text issue reports was accepted by TOSEM 2026.
- Our team received the Third Prize in the ChinaSoft 2025 National Prototype System Competition (SEAutoCMD).
- Our work on information-theft attacks in LLM tool-learning systems received the ACL 2025 SAC Highlight Award.
