Kaikai Zhang

I am a second-year Ph.D. student in the Department of Computer Science and Engineering at the Hong Kong University of Science and Technology (HKUST), advised by Prof. Dongdong She. I received my Bachelor’s degree in Computer Science and Technology from Shanghai Jiao Tong University (SJTU).

My research lies at the intersection of LLMs and cybersecurity, with a focus on advancing their capabilities on real-world security tasks such as vulnerability discovery, reproduction, patching and exploitation, as well as building more challenging and realistic benchmarks. Meanwhile, I am also exploring how to defend against these increasingly capable cyber agents. In addition, I am broadly interested in post-training and LLM/agent security. Currently, I am working as a research intern at Qwen, focusing on advancing the agentic cybersecurity capabilities of foundation models.

Please feel free to reach out via email at kzhangcq@connect.ust.hk or k.kaikaizhang@gmail.com.

Publications

RandSet: Randomized Corpus Reduction for Fuzzing Seed Scheduling

Yuchong Xie^*, Kaikai Zhang^*, Yu Liu, Rundong Yang, Ping Chen, Shuai Wang, and Dongdong She

ACM SIGPLAN Conference on Object-Oriented Programming, Systems, Languages, and Applications (OOPSLA 2026)

PDF Bib

@article{xie2026randset,
  title = {RandSet: Randomized Corpus Reduction for Fuzzing Seed Scheduling},
  author = {Xie, Yuchong and Zhang, Kaikai and Liu, Yu and Yang, Rundong and Chen, Ping and Wang, Shuai and She, Dongdong},
  journal = {ACM SIGPLAN Conference on Object-Oriented Programming, Systems, Languages, and Applications},
  volume = {10},
  number = {OOPSLA1},
  pages = {1570--1598},
  year = {2026},
  publisher = {ACM New York, NY, USA},
}

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, Ci Tao, Changhui Wang, Zongjie Li, Ping Chen, Shuai Wang, and Dongdong She

ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2026)

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 preprint (arXiv 2026)

PDF Bib

@misc{xie2026queryipi,
  title = {QueryIPI: Query-agnostic Indirect Prompt Injection on Coding Agents},
  author = {Xie, Yuchong and Liu, Zesen and Luo, Mingyu and Zhang, Zhixiang and Zhang, Kaikai and Yuan, Yuanyuan and Li, Zongjie and Chen, Ping and Wang, Shuai and She, Dongdong},
  year = {2026},
  eprint = {2510.23675},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2510.23675},
}

DDGF: Dynamic Directed Greybox Fuzzing with Path Profiling

Haoran Fang, Kaikai Zhang, Donghui Yu, and Yuanyuan Zhang

ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2024)

PDF Bib

@inproceedings{fang2024ddgf,
  title = {DDGF: Dynamic Directed Greybox Fuzzing with Path Profiling},
  author = {Fang, Haoran and Zhang, Kaikai and Yu, Donghui and Zhang, Yuanyuan},
  booktitle = {ACM SIGSOFT International Symposium on Software Testing and Analysis},
  pages = {832--843},
  year = {2024},
}

Internship Experience

Research Intern, Qwen, Cyber Team, 2026-07 ~ Present

Academic Service

Sub-Reviewer of ASE'25, TSE'25, CCS'26, ASE'26, ISSTA'26

Teaching Experience

Teaching Assistant, COMP 4634: Cybersecurity (Spring 2026, HKUST)