I am currently a research scientist at Singapore Management University, advised by Prof. David Lo.

Prior to that, I received my Ph.D. degree from Chongqing University, China, under the supervision of Dr. Meng Yan.

Research Interests

I have published over 35 papers citations 598 at top international conferences and journals in software engineering, artificial intelligence, and security, including ICSE, ASE, ISSTA, ACL, AAAI, TSE, TOSEM, and EMSE. My research lies at the intersection of artificial intelligence, software engineering, and software security. I am particularly interested in:

  • Security and Trustworthiness of Code LLMs: secure code generation and model editing (ISSTA’26, TSE’26), adversarial and jailbreak attacks on code models (ICSE’25, TSE’26, ACL’26), security risks of LLM long-term memory (ISSTA’26), social bias in LLM-generated code (ASE’26), and vulnerability detection (Internetware’24).
  • LLMs and Agents for Software Engineering: code generation (AAAI’26), generation-quality enhancement and knowledge distillation for code models (TOSEM’26, EMSE’26), LLM-based and multi-agent program repair (ASE’26), and reliability of agent systems (ASE’26).
  • Software Testing and Assertion Generation: assertion generation (ASE’23, TOSEM’24, TSE’25, ISSTA’26), testing of deep learning systems (TSE’23, TOSEM’24, TSE’25), and adaptive random testing and test prioritization (TSE’19, TR’19, TSE’24).
  • Software Evolution and Maintenance: test-to-code traceability and co-evolution (TOSEM’23, TSE’24), bug report understanding (JSS’23, ASEJ’25), method name updating (QRS’23), and security-fix backporting for CI/CD workflows (ICSE’27).

News

  • One paper on security-fix backporting for GitHub Actions workflows accepted to ICSE 2027.
  • Four papers accepted to ASE 2026, including our first-author study on how reasoning shapes social bias in LLM-generated code.
  • Three papers accepted to ISSTA 2026, including our first-author work on model editing for secure code generation.
  • MultiCodeAttack, our jailbreak attack on code LLMs, accepted to ACL 2026 Findings.
  • Our ICSE 2025 paper received an ACM SIGSOFT Distinguished Paper Award.

Selected Publications

View all

† first author · ✰ co-first author · * corresponding author

  1. ISSTA
    Understanding and Improving Model Editing for Secure Code Generation †
    Weifeng Sun, Quanjun Zhang, Yuchen Chen, Chengran Yang, Gou Tan, and David Lo
    In Proceedings of the ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA, CCF-A), 2026
  2. ASE
    How Reasoning Shapes Social Bias in LLM-Generated Code? †
    Weifeng Sun, Jieke Shi, Zhou Yang, Yuchen Chen, Hongyan Li, Meng Yan, and David Lo
    In Proceedings of the IEEE/ACM International Conference on Automated Software Engineering (ASE, CCF-A), 2026
  3. TSE
    Cost-Effective Adversarial Attacks Against Code LLM with Model Attention †
    Weifeng Sun, Naiqi Huang, Meng Yan, Li Huang, Zhongxin Liu, Xiao Liu, and David Lo
    IEEE Transactions on Software Engineering (TSE, CCF-A), 2026
  4. TOSEM
    On-the-Fly Generation-Quality Enhancement of Deep Code Models via Model Collaboration †
    Weifeng Sun, Naiqi Huang, Meng Yan, Zhongxin Liu, Hongyan Li, Yan Lei, and David Lo
    ACM Transactions on Software Engineering and Methodology (TOSEM, CCF-A), 2026
  5. ACL Findings
    MultiCodeAttack: Iterative Jailbreak Attacking on LLMs with Multi-Code Prompt Injection †
    Weifeng Sun, Meng Yan, Zhou Yang, Yuchen Chen, Song Sun, and David Lo
    In Findings of the Association for Computational Linguistics: ACL 2026 (ACL, CCF-A), 2026
  6. TSE
    Method-Level Test-to-Code Traceability Link Construction by Semantic Correlation Learning †
    Weifeng Sun, Zhenting Guo, Meng Yan, Zhongxin Liu, Yan Lei, and Hongyu Zhang
    IEEE Transactions on Software Engineering (TSE, CCF-A), 2024
  7. TSE
    Robust Test Selection for Deep Neural Networks †
    Weifeng Sun, Meng Yan, Zhongxin Liu, and David Lo
    IEEE Transactions on Software Engineering (TSE, CCF-A), 2023
  8. TOSEM
    Revisiting the Identification of the Co-Evolution of Production and Test Code †
    Weifeng Sun, Meng Yan, Zhongxin Liu, Xin Xia, Yan Lei, and David Lo
    ACM Transactions on Software Engineering and Methodology (TOSEM, CCF-A), 2023
  9. ASE
    Revisiting and Improving Retrieval-Augmented Deep Assertion Generation †
    Weifeng Sun, Hongyan Li, Meng Yan, Yan Lei, and Hongyu Zhang
    In The 38th IEEE/ACM International Conference on Automated Software Engineering (ASE, CCF-A), Full paper, 2023
  10. TSE
    A survey on adaptive random testing †
    Rubing Huang, Weifeng Sun, Yinyin Xu, Haibo Chen, Dave Towey, and Xin Xia
    IEEE Transactions on Software Engineering (TSE, CCF-A), 2019
  11. TSE
    Retrieval-Augmented Fine-Tuning for Improving Retrieve-and-Edit Based Assertion Generation ✰
    Hongyan Li, Weifeng Sun, Meng Yan, Ling Xu, Qiang Li, Xiaohong Zhang, and Hongyu Zhang
    IEEE Transactions on Software Engineering (TSE, CCF-A), 2025
  12. TOSEM
    Exploring Automated Assertion Generation via Large Language Models ✰
    Quanjun Zhang, Weifeng Sun, Chunrong Fang, Bowen Yu, Hongyan Li, Meng Yan, Jianyi Zhou, and Zhenyu Chen
    ACM Transactions on Software Engineering and Methodology (TOSEM, CCF-A), 2024
  13. TOSEM
    Neuron Semantic-Guided Test Generation for Deep Neural Networks Fuzzing ✰
    Li Huang, Weifeng Sun, Meng Yan, Zhongxin Liu, Yan Lei, and David Lo
    ACM Transactions on Software Engineering and Methodology (TOSEM, CCF-A), 2024

Experience & Education

  • Research Scientist, Singapore Management University
  • Ph.D. in Software Engineering, Chongqing University
  • M.A.Sc. in Software Engineering, Jiangsu University
  • B.Eng. in Software Engineering, Jiangsu University

Awards

  • ACM SIGSOFT Distinguished Paper Award, ICSE 2025
  • Young Elite Scientists Sponsorship Program (Doctoral Student Special Plan), CAST
  • National Scholarship, Ministry of Education
  • National Scholarship, Ministry of Education
  • National Scholarship, Ministry of Education