Chenyuan Yang

Chenyuan Yang

PhD student at UIUC

About

I am Chenyuan Yang (杨晨源), a PhD student at UIUC advised by Prof. Lingming Zhang since 2022 Fall.

I received my B.S. degree with honors from the elite program in the Department of Computer Science & Technology at Nanjing University, advised by Prof. Yanyan Jiang.

My research focuses on enhancing the reliability of software systems, such as machine learning systems, compilers, and OS kernels. To achieve this, I employ a combination of testing, analysis, and verification techniques, with a particular emphasis on leveraging the power of large language models (LLMs).

To date, my work has uncovered over 400 previously unknown bugs in widely-used machine learning systems, including PyTorch, TensorFlow, JAX, as well as 9 CVEs for the Linux kernel.

Besides deep learning systems and the Linux kernel, I also reported more than 30 bugs for other open-source projects, such as NumPy, Moby, and VSCode-Vim.

Selected Publications

For a full list of publications, please refer to Publications.

  • [Preprint] KNighter: Transforming Static Analysis with LLM-Synthesized Checkers
    Chenyuan Yang, Zijie Zhao, Zichen Xie, Haoyu Li, Lingming Zhang
    (Preprint), Mar 2025. [paper] [code]
  • [Preprint] AutoVerus: Automated Proof Generation for Rust Code
    Chenyuan Yang, Xuheng Li, Md Rakib Hossain Misu, Jianan Yao, Weidong Cui, Yeyun Gong, Chris Hawblitzel, Shuvendu Lahiri, Jacob R. Lorch, Shuai Lu, Fan Yang, Ziqiao Zhou, Shan Lu
    (Preprint), Sept 2024. [website] [paper]
  • KernelGPT: Enhanced Kernel Fuzzing via Large Language Models
    Chenyuan Yang, Zijie Zhao, Lingming Zhang
    30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems
    (ASPLOS 2025), March 2025. [paper] [code]
  • WhiteFox: White-box Compiler Fuzzing Empowered by Large Language Models
    Chenyuan Yang, Yinlin Deng, Runyu Lu, Jiayi Yao, Jiawei Liu, Reyhaneh Jabbarvand, Lingming Zhang
    Object-Oriented Programming, Systems, Languages, and Applications 2024 (in PACM PL)
    (OOPSLA 2024), Oct 2024. [paper] [code] [slides]
  • Large Language Models are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models
    Yinlin Deng, Chunqiu Steven Xia, Haoran Peng, Chenyuan Yang, Lingming Zhang
    32nd International Symposium on Software Testing and Analysis
    (ISSTA 2023), July 2023. [paper]
  • Fuzzing Automatic Differentiation in Deep-Learning Libraries
    Chenyuan Yang, Yinlin Deng, Jiayi Yao, Yuxing Tu, Hanchi Li, Lingming Zhang
    45th International Conference on Software Engineering
    (ICSE 2023), May 2023. [paper] [code] [slides]

    • * denotes joint first authors

    Internships

    Microsoft Research, Systems Research Group Summmer 2024

    Google Labs, Project Starline Summmer 2023

    Talks

    Fuzzing Deep-Learning Libraries via Automated Relational API Inference

    • Software Engineering Retreat, University of Illinois at Urbana-Champaign, Sept. 2022

    Free Lunch for Testing: Fuzzing Deep-Learning Libraries from Open Source