Junming Liu
刘君茗

Master's student with research interests in
Large Language Models for Software Security,
Software Engineering, and
Program Analysis.

About Me

Hi, my name is Junming Liu (刘君茗). I am currently a Master's student in Zhejiang University, under the supervision of Prof. Wenhai Wang. My research interests in Large Language Models for Software Security, Software Engineering, and Program Analysis.

My research interests focuses on improving the effectiveness and quality of the entire vulnerability management lifecycle, with two key aspects:

  • Advancing vulnerability management technologies, including vulnerability detection, automated fixing, patch correctness assessment, and more.
  • Understanding the broader societal and community impacts of vulnerabilities.

To achieve these goals, I am interested in exploring the use of machine learning, static analysis, and other techniques to enhance vulnerability management. I also seek to assess how these tools can improve both technical efficiency and the human-centered understanding of vulnerabilities.

Email: jmliu|at|zju.edu.cn

Resume

News 🔥

Nov 2024
I will serve as an Artifact Evaluation Committee member of USENIX Security 2025.
Aug 2024
I presented our evaluation for ChatGPT's capabilities on vulnerability management at USENIX Security 2024 in Philadelphia.
Jun 2024
Our paper "Exploring ChatGPT's Capabilities on Vulnerability Management" was accepted by USENIX Security 2024.

Publications

Conference Paper
(*equal contribution)

Exploring ChatGPT's Capabilities on Vulnerability Management
Peiyu Liu*,
Junming Liu*
, Lirong Fu, Kangjie Lu, Yifan Xia, Xuhong Zhang, Wenzhi Chen, Haiqin Weng, Shouling Ji, Wenhai Wang.
USENIX Security 2024
Evaluation of ChatGPT’s capabilities across the entire vulnerability management lifecycle in six tasks, investigating prompt engineering impacts and identifying performance bottlenecks.
sym

Service

Artifact Evaluation Committee

  • USENIX Security 2025