About me

Bio

Hi! This is Weipeng Jiang (降伟鹏). I am a third-year Ph.D. student in School of Cyber Science and Engineering at Xi’an Jiaotong University. As a member of the Laboratory for Advanced Computing and Intelligent Security, I am being advised by Prof.Chao Shen. Additionally, I am also very fortunate to work closely with Prof.Juan Zhai and Prof.Shiqing Ma.

My research interests encompass Software Engineering for AI systems (SE4AI) and AI for Software Engineering (AI4SE). Specifically, I am actively involved in the following topics:

  • Effective and Efficient Auditing and Red Teaming for LLM Safety, Fairness, and Privacy.
  • Assessment and Enhancement of LLM4Code Applications.
  • Defect Testing and Analysis in Deep Learning Frameworks and Dependency Libraries.

News

  • [Aug 2024] Be invited to serve as a reviewer ICLR 2025.
  • [June 2024] New preprint is online Unlocking Adversarial Suffix Optimization Without Affirmative Phrases: Efficient Black-box Jailbreaking via LLM as Optimizer.
  • [Aug 2024] Be invited to serve as a program committee of Artifact Evaluation Track for ICSE 2025.
  • [June 2024] New preprint is online From Effectiveness to Efficiency: Comparative Evaluation of Code Generated by LCGMs for Bilingual Programming Questions.
  • [May 2024] Be invited to serve as a reviewer for NeurIPS 2024.
  • [Feb 2024] Our paper about Embedding-Service Testing is accepted by FSE'24.
  • Publications.

    • Unlocking Adversarial Suffix Optimization Without Affirmative Phrases: Efficient Black-box Jailbreaking via LLM as Optimizer
      Weipeng Jiang, Zhenting Wang, Juan Zhai, Shiqing Ma, Zhengyu Zhao, Chao Shen
      arXiv preprint, August 2024
      [Paper]

    • Efficient DNN-Powered Software with Fair Sparse Models
      Xuanqi Gao, Weipeng Jiang, Juan Zhai, Shiqing Ma, Xiaoyu Zhang, Chao Shen
      ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2024)
      Vienna, Austria, September 2024 [Paper]

    • From Effectiveness to Efficiency: Comparative Evaluation of Code Generated by LCGMs for Bilingual Programming Questions
      Weipeng Jiang, Xuanqi Gao, Juan Zhai, Shiqing Ma, Xiaoyu Zhang, Chao Shen
      arXiv preprint, June 2024
      [Paper]

    • A Survey of Deep Learning Library Testing Methods.
      Xiaoyu Zhang, Weipeng Jiang, Chao Shen, Qi Li, Qian Wang, Chenhao Lin, Xiaohong Guan
      arXiv preprint, April 2024
      [Paper]

    • COSTELLO: Contrastive Testing for Embedding-based Large Language Model as a Service Embeddings
      Weipeng Jiang, Juan Zhai, Shiqing Ma, Xiaoyu Zhang, Chao Shen.
      Proceedings of the ACM International Conference on the Foundations of Software Engineering (FSE24, Direct Acceptance Rate 11.8%)
      Porto de Galinhas, Brazil, July 2024
      [Paper], [Code]

    • Fairness in Machine Learning: Definition, Testing, Debugging and Application
      Xuanqi Gao, Chao Shen, Weipeng Jiang, Chenhao Lin, Qian Li, Qian Wang, Qi Li, Xiaohong Guan
      Science China Information Sciences[J] (SCIS), June 2024 [Paper]

    • Black-Box Fairness Testing with Shadow Models
      Weipeng Jiang, Chao Shen, Chenhao Lin, Jingyi Wang, Jun Sun, Xuanqi Gao
      International Conference on Information and Communications Security, Nov 2023 (ICICS23) [Paper], [Code]

    Teaching

    • Teaching Assistant, COMP251905: Data Structures and Algorithms, Xi’an Jiaotong University, Fall 2021
    • Teaching Assistant, Olympiad in Informatics, Jisuanke, Summer 2019

    Award

    • ACMSIG Travel Grants, 2024
    • Outstanding Graduates, Xi’an Jiaotong University, 2021
    • Lu-Shidi Scholarship (Top-5 students in Computer Science School), Xi’an Jiaotong University, 2019
    • Silever Award in Collegiate Computer Systems & Programming Contest (CCSP), China Computer Federation, 2018/2019
    • Silever Award in The International Collegiate Programming Contest of Asia Regional (ACM-ICPC), Association for Computing Machinery, * * 2018/2019