Ziyou Jiang

Ziyou Jiang

Postdoctoral Researcher, Institute of Software, Chinese Academy of Sciences (ISCAS)

中文简历

我目前是中国科学院软件研究所智能博弈重点实验室的博士后研究人员。我的研究主要聚焦于群体知识抽取与分析、面向软件安全的威胁分析、漏洞识别与自动修复、LLM 工具学习系统安全，以及 AIGC 生成多模态内容的安全风险。

教育与任职

研究方向

第一作者论文

  1. 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]
  2. 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]
  3. 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]
  4. 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]
  5. Ziyou Jiang, Lin Shi, Guowei Yang, Qing Wang. SCPatcher: Mining Crowd Security Discussions to Enrich Secure Coding Practices. ASE 2023: 358-370. [Paper]
  6. 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]
  7. 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]
  8. Ziyou Jiang, Lin Shi, Celia Chen, Jun Hu, Qing Wang. Dialogue Disentanglement in Software Engineering: How Far Are We? IJCAI 2021: 3822-3828. [Paper]

合作论文精选

  1. 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.
  2. 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.
  3. 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.
  4. 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]
  5. 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]
  6. 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]
  7. 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]
  8. 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]

学术服务

项目

荣誉与奖励

学术报告

最新动态