I am a sixth-year direct-track Ph.D. student at the Institute of Software, Chinese Academy of Sciences, affiliated with the Key Laboratory of Intelligent Game. I am fortunate to be advised by Assoc. Research Fellow Mingyang Li and Research Fellow Qing Wang during my doctoral studies. Previously, I was a visiting student at the School of Computer Science and Engineering, Nanyang Technological University (NTU), supervised by Prof. Yang Liu.
To date, I have published 10 papers in top conferences and journals in both software engineering (ICSE, FSE, TOSEM) and natural language processing (ACL, EMNLP). Currently, my research interests focus on LLM security（especially in the areas of LLM agents and RAG), AI model testing, and intelligent requirements engineering. I am always open to discussions and collaborations—please feel free to reach out!
🔥News
- [2026.04] 🎉🎉 Two papers were accepted by accepted the ACL 2026!
- [2025.08] 🎉🎉 Two papers were accepted by accepted the EMNLP 2025!
- [2025.04] 🎉🎉 One paper was accepted by the ACL 2025!
- [2025.04] 🎉🎉 One paper was accepted by the TOSEM!
- [2024.08] 🎉🎉 One paper was accepted by the EMNLP 2024!
- [2024.04] 🎉🎉 One paper was accepted by the ACL 2024!
📝 Publications
-
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. In Annual Conference of the Association for Computational Linguistics (ACL), 2026. (CCF-A) [PDF] -
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. In Annual Conference of the Association for Computational Linguistics (ACL), 2026. (CCF-A) [PDF] -
Zhiyuan Chang, Mingyang Li, Xiaojun Jia, Junjie Wang, Yuekai Huang, Qing Wang, Ziyou Jiang, Yang Liu. One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems. In Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025. (CCF-B) [PDF] -
Qian Xiong, Yuekai Huang, Ziyou Jiang,
Zhiyuan Chang, Yujia Zheng, Tianhao Li, Mingyang Li. Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems. In Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025. (CCF-B) [PDF] -
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. In Annual Conference of the Association for Computational Linguistics (ACL), 2025. (CCF-A) [PDF] SAC Highlight Award🏆 -
Zhiyuan Chang, Mingyang Li, Yi Liu, Junjie Wang, Qing Wang, Yang Liu. Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues. In Annual Conference of the Association for Computational Linguistics (ACL), 2024. (CCF-A) [PDF] -
Zhiyuan Chang, Mingyang Li, Junjie Wang, Cheng Li, Qing Wang. VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing. In ACM Transactions on Software Engineering and Methodology (TOSEM). (CCF-A) [PDF] -
Zhiyuan Chang, Mingyang Li, Junjie Wang, Yi Liu, Qing Wang, Yang Liu. Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement. In Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024. (CCF-B) [PDF] -
Zhiyuan Chang, Mingyang Li, Qing Wang, Shoubin Li, Junjie Wang. Cross-domain requirements linking via adversarial-based domain adaptation. In IEEE/ACM 45th International Conference on Software Engineering (ICSE), 2023. (CCF-A) [PDF] -
Zhiyuan Chang, Mingyang Li, Junjie Wang, Qing Wang, Shoubin Li. Putting them under microscope: a fine-grained approach for detecting redundant test cases in natural language. In Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE), 2022. (CCF-A) [PDF]
📚 Services
Reviewer of IEEE Transactions on Software Engineering
Reviewer of Annual Conference of the Association for Computational Linguistics
Reviewer of Conference on Empirical Methods in Natural Language Processing