Hongwei Li(李洪伟)

Ph.D. Student at UC Santa Barbara

AI for Security (AI4Sec) Researcher

About Me

Download CV

I am a Ph.D. student at the University of California, Santa Barbara, working under the supervision of Dr. Wenbo Guo. I am a member of Shellphish, a renowned cybersecurity research group, and a core member of the ARTIPHISHELL team that competed in the DARPA AI Cyber Challenge (AIxCC).

Education

University of California, Santa Barbara
Ph.D. in Computer Science

2024 - Present

Current
Purdue University
Ph.D. in Computer Science (First Year)

September 2023 - May 2024

Completed
Shanghai Jiao Tong University
Master of Engineering in Electronic Information

September 2020 - June 2023

Completed
Shanghai Jiao Tong University
Bachelor of Arts in French & Bachelor of Engineering in Information Engineering

September 2016 - June 2020

Completed

Research Interests

AI for Security (AI4Sec)

Developing AI-driven approaches to improve cybersecurity effectiveness.

Reinforcement Learning for Fuzzing

Using reinforcement learning to assist collaborative fuzzing techniques.

LLMs for Automatic Patching

Leveraging large language models to automatically generate and apply security patches.

Software Security

Vulnerability detection, analysis, and remediation techniques.

Selected Competitions

DARPA AIxCC Finalist (5th Place)

Core member of the ARTIPHISHELL team that advanced to the finals of the DARPA AI Cyber Challenge (AIxCC). Team won $2 million in semifinal competition.

My Role & Contributions:

During the early stages, I served as a core member of the patching team, focusing on automated vulnerability patching. As the competition progressed to the final phase, my responsibilities expanded to include custom model fine-tuning for vulnerability detection, contributing to the development of the root cause analysis engine kumu-shi, and supporting the maintenance of our patching tool named PatcherY.

Media Coverage:
First Place in SBFT 2024 Fuzzing Competition

BandFuzz won the SBFT 2024 Fuzzing Competition, which uses mutation testing as the ranking metric. Our framework achieved the best performance across all evaluation metrics among all competing teams, including the highest number of mutant kills, the highest average mutation score, and the highest coverage of mutants.

Competition Summary
Media Coverage:
Northwestern Media Coverage
SBFT 2024 First Place Certificate

Click image to view full size

CTFs
DEF CON CTF 2025 final (11th Place)
Member of the Shellphish team
SunshineCTF 2021 (11th Place)
Solo team in a team-based CTF competition

Publications

LLM post-training and agents
  1. Yuzhou Nie, Hongwei Li, Ruizhe Jiang, Chengquan Guo, Zhun Wang, Bo Li, Dawn Song, Wenbo Guo, “VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection”, Submitted to The 47th IEEE Symposium on Security and Privacy, Rio de Janeiro, Brazil, 2026.
  2. Shellphish, “An AI-powered Cyber Reasoning System for Automatic Vulnerability Identification and Patching”, Submitted to Phrack Papers, 2026.
  3. Yuheng Tang, Kaijie Zhu, Bonan Ruan, Chuqi Zhang, Michael Yang, Hongwei Li, Suyue Guo, Tianneng Shi, Zekun Li, Christopher Kruegel, Giovanni Vigna, Dawn Song, William Yang Wang, Lun Wang, Yangruibo Ding, Zhenkai Liang, Wenbo Guo, “DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle”, Submitted to The 14th International Conference on Learning Representations, 2026.
  4. Tianneng Shi, Jingxuan He, Zhun Wang, Linyu Wu, Hongwei Li, Wenbo Guo, Dawn Song, “Progent: Programmable Privilege Control for LLM Agents”, Submitted to The 47th IEEE Symposium on Security and Privacy, Rio de Janeiro, Brazil, 2026.
  5. Yujin Potter, Wenbo Guo, Zhun Wang, Tianneng Shi, Hongwei Li, Andy Zhang, Patrick Gage Kelley, Kurt Thomas, Dawn Song, “SoK: Frontier AI’s Impact on the Cybersecurity Landscape”, Submitted to The 47th IEEE Symposium on Security and Privacy, Rio de Janeiro, Brazil, 2026.
  6. [ICML’25] Hongwei Li, Yuheng Tang, Shiqi Wang, Wenbo Guo, “PatchPilot: A Verifiable and Cost-Efficient Agentic Patching Framework”, In Proceedings of The 42nd International Conference on Machine Learning, Vancouver, CA, 2025.
  7. [NeurIPS’25] Yuheng Tang, Hongwei Li, Kaijie Zhu, Michael Yang, Yangruibo Ding, Wenbo Guo, “Co-PatcheR: Collaborative Software Patching with Component-specific Small Reasoning Models”, In Proceedings of The 39th Conference on Neural Information Processing Systems, San Diego, CA, 2025.
RL and DNN for Security
  1. Wenxuan Shi, Hongwei Li, Jiahao Yu, Xinqian Sun, Wenbo Guo, Xinyu Xing, “BandFuzz: An ML-powered Collaborative Fuzzing Framework.”, arXiv preprint arXiv:2507.10845.
  2. [ICSE SBFT’24] Wenxuan Shi, Hongwei Li, Jiahao Yu, Wenbo Guo, Xinyu Xing, “BandFuzz: A Practical Framework for Collaborative Fuzzing with Reinforcement Learning”, In Proceedings of the International Workshop on Search-Based and Fuzz Testing, Lisbon, Portugal, 2024.
  3. [Computers & Security’22] Jingcheng Yang, Hongwei Li, Shuo Shao, Futai Zou, Yue Wu, “FS-IDS: A framework for intrusion detection based on few-shot learning”, Computers & Security, 122:102899, 2022.