Zesen Liu (刘泽森)

Portrait of Zesen Liu

I am a Ph.D. student in the CSE Department at HKUST, supervised by Prof. Dongdong She. Before coming to HKUST, I earned my bachelor's degree from Xidian University.

My research studies how to make the reasoning processes of agentic systems more reliable and safe. I pursue two complementary directions: designing system-level harness from human knowledge and rules, and developing interactive environments for agentic reinforcement learning that improve planning, verification, tool use, and action through long-horizon agentic reasoning process.

Contact: zliuhi at cse dot ust dot hk, Google Scholar, GitHub

Publications and Preprints

Safe to Check, Unsafe to Use: Relinking at the Compression Boundary of LLM Agents
Zesen Liu, Zihan Zhang, and Dongdong She
arXiv:2606.21732arXiv
When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents
Zesen Liu, Zhixiang Zhang, Yuchong Xie, and Dongdong She
IEEE/ACM International Conference on Automated Software Engineering (ASE 2026)arXiv
From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
Zhixiang Zhang, Zesen Liu, Yuchong Xie, Quanfeng Huang, and Dongdong She
International Conference on Machine Learning (ICML 2026)arXiv
Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment
Yuchong Xie, Mingyu Luo, Zesen Liu, Zhixiang Zhang, Kaikai Zhang, Yu Liu, Zongjie Li, Ping Chen, Shuai Wang, and Dongdong She
ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2026)arXiv
Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging
Tianshuo Cong, Delong Ran, Zesen Liu, Xinlei He, Yichen Gong, Jinyuan Liu, Qi Li, Anyu Wang, and Xiaoyun Wang
The 1st ACM Workshop on Large AI Systems and Models with Privacy and Safety Analysis, co-located with ACM CCS 2024 (CCS-LAMPS 2024). Best Paper Award
OBIR-tree: An Efficient Oblivious Index for Spatial Keyword Queries on Secure Enclaves
Zikai Ye, Xiangyu Wang, Zesen Liu, Dan Zhu, and Jianfeng Ma
ACM SIGMOD International Conference on Management of Data (SIGMOD 2025)
When Alignment Isn’t Enough: Response-Path Attacks on LLM Agents
Mingyu Luo, Zihan Zhang, Zesen Liu, Yuchong Xie, Zhixiang Zhang, Dung Hiu Hilton Yeung, Wai Ip Lai, Ping Chen, Ming Wen, and Dongdong She
arXiv:2605.02187arXiv
QueryIPI: Query-agnostic Indirect Prompt Injection on Coding Agents
Yuchong Xie, Zesen Liu, Mingyu Luo, Zhixiang Zhang, Kaikai Zhang, Yuanyuan Yuan, Zongjie Li, Ping Chen, Shuai Wang, and Dongdong She
arXiv:2510.23675arXiv
On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks
Zesen Liu, Tianshuo Cong, Xinlei He, and Qi Li
arXiv:2407.04794arXiv

Experience

  • Research Assistant, Tsinghua University and HKUST(GZ), October 2023 - July 2024

Academic Service

  • Reviewer, ICML 2026
  • Sub-reviewer, CCS 2026, ISSTA 2026, FSE 2025, S&P 2025

Honors and Awards

  • 2026.07 Research Travel Grant
  • 2026.05 Gold Reviewer of ICML
  • 2025.06 Overseas Study Scholarship
  • 2024.11 Gratitude to Chinese Modern Scientists Scholarship
  • 2024.10 Best Paper Award of CCS-LAMPS
  • 2024.10 National Scholarship
  • 2024.06 Qi'an Xin Scholarship
  • 2021-2024 First Prize Scholarship