Ziyou Jiang's Profile

Personal Information

My name is Ziyou Jiang, the Postdoctoral Researcher in Software Engineering. I am working in State Key Laboratory of Intelligent Game in Institute of Software, Chinese Academy of Sciences (ISCAS).

• From 2015~2019, I received my B.S. in Software Engineering (School of Software), Xiamen University.
• From 2019~2025, I received my Ph.D. in ISCAS, advised by Prof. Qing Wang (Senior Researcher).
• From 2025~, I am working as a Postdoctoral Researcher in ISCAS, advised by Prof. Qing Wang.
• From 2025~, I am working as a Self-Employed Researcher in SIGMIR.

My major research directions are crowd-based knowledge extraction and analysis, software security oriented threat analysis and vulnerability detection and fixing. Nowadays, I’m also working on the LLM security, especially the threat analysis and vulnerability identification in LLM tool-learning systems, as well as the security in AIGC-generated multimodal elements.

Publication

[1] 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. SAC Highlight Award. [Paper]

[2] 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]

[3] Ziyou Jiang, Lin Shi, Guowei Yang, Qing Wang: SCPatcher: Mining Crowd Security Discussions to Enrich Secure Coding Practices. ASE 2023: 358-370. [Paper]

[4] 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]

[5] Lin Shi and 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. ACM Distinguished Paper Award. [Paper]

[6] Ziyou Jiang, Lin Shi, Celia Chen, Jun Hu, Qing Wang: Dialogue Disentanglement in Software Engineering: How Far are We? IJCAI 2021: 3822-3828. [Paper]

[7] Qian Xiong and 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]

[8] 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]

[9] 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]

[10] 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]

Referee

Program Committee

• Transaction on Software Engineering (TSE), CCF-A, Core A*, Top Journal in SE
• Transaction on Big Data (TBD), Top Journal in BigData
• AAAI Conference on Artificial Intelligence (AAAI), CCF-A, Core A*, Top Conference in AI

Assistant Referee

• Conference: ASE, ICSE, ESEC/FSE
• Journal: TOSEM

Project

• 2024, National Key Research and Development Projects of China, i.e., Security Risks in AIGC-Generated Multimodal Contents. Project Secretary, Core R&D Personnel
• 2021, Huawei Poplar Forest Fund, Core R&D Personnel

Award

• 2025, Excellent Poster Award, ISCAS Academic Annual Conference (中科院软件所学术年会优秀海报奖)
• 2025, SAC Highlights Award, ACL 2025 (CCF-A, Core A*, NLP Top Conference)
• 2025, Outstanding Scholarship for President of the Chinese Academy of Sciences (中国科学院院长优秀奖学金)
• 2024, Three Good Students, University of Chinese Academy of Sciences (中国科学院大学三好学生)
• 2022, Three Good Students, University of Chinese Academy of Sciences (中国科学院大学三好学生)
• 2021, Representative Accomplishments, ISCAS Academic Annual Conference (中科院软件所学术年会代表性成果)
• 2021, ACM Distinguished Paper Award, ASE 2021 (CCF-A, Core A*, SE Top Conference)
• 2017, National Third Prize, The Chinese University Student’s Service Outsourcing Innovation and Entrepreneurship Competition: Team Leader of Status 200 (中国大学生服务外包大赛全国三等奖)
• 2017, Fujian Province’s Second Prize, The Chinese University Student’s Mathematical Modeling Competition (中国大学生数学建模大赛福建省二等奖)
• 2018, Hua-Bin QIU Scholarship, Xiamen University Anniversary Celebration (厦门大学邱华炳奖学金)
• 2017, Academic First-Class Scholarship, Xiamen University (厦门大学学业优秀一等奖学金)
• 2017, Academic Innovation Scholarship, Xiamen University (厦门大学学术创新奖学金)

Talk

• 2025, ACL’25 Conference, Poster Presentation of “Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System”
• 2024, Graduate Academic Forum of University of Chinese Academy of Sciences, Poster Presentation
• 2024, ASE’24 Conference, Presentation of “PatUntrack: Automated Generating Patch Examples for Issue Reports without Tracked Insecure Code”
• 2023, ASE’23 Conference, Presentation of “SCPatcher: Mining Crowd Security Discussions to Enrich Secure Coding Practices”
• 2021, ChinaSoft, Forum of Top Conference and Journal, Online Presentation

Social Activity

I am also the psychological committee member in the laboratory, and enjoy playing piano and football and go hiking. In fact, when I was in the preliminary school, my major is piano lol :) (amateur level, not professional).

I prefer sharing with my new thoughts with you in the leisure time, and do not be too strict. To be honest, I think the researchers need to be happy and enthusiastic, not always work by yourself.

My Motto

• Always be enthusiastic and powerful to the new research.
• Always write down the useful and necessary papers for the society.

Latest News

• Our research on LLM jailbreak in multi-turn dialogue is accepted by EMNLP’25 Finding!
• Our research on the parameter filling in LLM tool-learning system is accepted by EMNLP’25 Finding!
• Our research on the information-theft attack in LLM tool-learning system is awarded SAC Highlights Award by ACL’25!
• I’m working on the National Key Research and Development Projects, i.e., Security Risks in AIGC-Generated Multimodal Contents.
• I’m working on the automated threat modeling for LLM tool-learning systems and MCP, cuz it is too difficult via the human designing.