Cheng Wen

Associate Research Fellow
Guangzhou Institute of Technology, Xidian University


Pseudonym : wcventure
Name : Cheng Wen
Institution : Guangzhou Institute of Technology,
Xidian University
Email : wencheng[at]xidian.edu.cn
Skype : wcventure
Address : Guangzhou City, Guangdong Province,
China, 510530
Homepage : https://wcventure.github.io/
Github : https://github.com/wcventure
CSDN : https://blog.csdn.net/wcventure
Google Scholar : https://scholar.google.com/citations?hl=en&user=wcventure

  文成雕龙与天骄，
  心若白云常自在。
  雕陂之水清且泚，
  龙归洞府暮将雨！

  Cheng Wen
signature

About Me

Cheng Wen is an associate research fellow and master's supervisor at the Guangzhou Institute of Technology, Xidian University. He received his Ph.D. in Computer Science and Technology from Shenzhen University in December 2022. His earlier experience includes approximately one year as a visiting researcher at Nanyang Technological University, Singapore, and around two years of industrial research and practice at Huawei Technologies.
His research focuses on software engineering, trustworthy software, and large language models, particularly AI-assisted software testing and verification, formal specification synthesis, program analysis, fuzzing, concurrency testing, and formal verification. He has authored or coauthored over 60 publications in venues including CAV, FM, ICSE, ASE, FSE, ACL, KDD, NeurIPS, ISSRE, ESEM, TPDS, TKDD, and Information Fusion. His research has received the ACM SIGSOFT Distinguished Paper Award at ASE 2025, a CCL 2026 Highlight Paper recognition, the ICRMS 2026 Best Paper Award, and the FMAC 2018 Best Paper Award.
His proposed methods and tools have been applied to aerospace control software development and verification and deployed in Huawei's Fema platform and multiple product lines. His software testing and security research has identified hundreds of defects in open-source software, including 80+ assigned CVE identifiers.
More information here.

  Education

  • ShenZhen University, ShenZhen, China

    • Ph.D in Computer science and technology
    • September 2019 – December 2022
    • Supervisor: Prof. Shengchao Qin

  • ShenZhen University, ShenZhen, China

  • ShenZhen University, ShenZhen, China

    • B.S. in Software Engineering
    • September 2011 – June 2015

  Work Experience

  • Xidian University, Guangzhou, China

    • Lecturer in Guangzhou Institute of Technology
    • December 2022 – Now

  Research Experience

  • Huawei Technologies Co., Ltd, Shenzhen, China

    • Intern in Trustworthiness Testing Engineering Lab
    • September 2021 – December 2022
    • Duties included: Controlled Concurrency Testing via Periodical Scheduling, Program Verification with CBMC.

  • Huawei Technologies Co., Ltd, Dongguan, China

    • Intern in Data Communication Trustworthiness Enabling and IPD Dept
    • September 2020 – March 2021
    • Duties included: Formal verification of Secure Boot Module.

  • Nanyang Technological University, Singapore

    • Visiting researcher
    • July 2018 – July 2019
    • Duties included: MemLock: Memory Usage Guided Fuzzing; Typestate-Guided Fuzzer for Discovering Use-after-Free Vulnerabilities.
    • Co-supervisor: Prof. Yang Liu

  Pulications

  See also at Google Scholar and DBLP.

2027

  1. Cheng Wen, Junjie Hu, Wenjie Wu, Bin Yu, Shengchao Qin.
    Verifier-Constrained Neural-Symbolic Synthesis of Formal Program Specifications.
    Data Intelligence. 2027. (Data Intelligence 2027, CAS Q2)
    CCL 2026 Highlight Paper

2026

  1. Zhi Ma, Xiao Liang, Cheng Wen, Rui Chen, Bin Gu, Shengchao Qin, Cong Tian, Mengfei Yang.
    Automated LTL Specification Generation from Industrial Aerospace Requirements.
    Proceedings of the 27th International Symposium on Formal Methods. LNCS, vol. 16557, 2026: 670–690. (FM 2026, CCF A, corresponding author)
    PDF, DOI
  2. Zhi Ma, Cheng Wen, Bin Yu, Jie Su.
    Integrating ensemble learning and Large Language Models for efficient formal verification of IP-based aerospace systems.
    Information Fusion, 2026, 125: 103466. (INFFUS 2026, CAS Q1, corresponding author)
    DOI
  3. Jiaxin Xi, Cheng Wen, Zhiwei Lin, Yuandao Cai, Jie Su, Bin Yu, Zhuohua Li, Shengchao Qin.
    Understanding the Performance-Effectiveness Trade-Offs of AddressSanitizer in Real-World Programs: An Empirical Study.
    Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering. 2026: 3816–3828. (ASE 2026 Industry Showcase, CCF A, corresponding author)
    DOI, Video, Code
  4. Shaohao Wang, Cheng Wen, Yuandao Cai, Shengchao Qin, Jie Su, Mengda He, Xiaoxue Ma, Cong Tian.
    Understanding Real-World Ordering-Related Concurrency Bugs under Weak-Memory and Cross-Architecture Settings.
    Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering. 2026: 4030–4041. (ASE 2026 Industry Showcase, CCF A, corresponding author)
    DOI, Video, Code
  5. Dugang Liu, Ding Wang, Chao Jiang, Cheng Wen, Zhiwu Xu, Zhong Ming, Yuwei Liu, Xinyi Wan, Lin Huang.
    Beyond Benchmarks: A Case Study of LLM-Generated Verus Specification Failures on Asterinas Vostd.
    Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering. 2026: 4152–4163. (ASE 2026 Industry Showcase, CCF A)
    DOI, Code
  6. Cheng Wen, Junjie Hu, Yikun Hu, Jie Su, Bin Yu, Dugang Liu, Zhiwu Xu, Weidi Sun, Shengchao Qin, Cong Tian.
    Formally Specifying the Intended Behavior of the Program: LLM-Driven Neuro-Symbolic Program Specification Synthesis.
    Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). 2026: 672–682. (ACL Demo 2026, CCF A)
    PDF, DOI, Video, Code, DataSet
  7. Cheng Wen, Wenjun Ke, Xiao Liang, Zhi Ma, Xiaoyong Xue, Shengchao Qin, Cong Tian.
    TLCrafter: Peeling the Layers of Natural Language to Reveal Temporal Logic Specifications.
    Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering. 2026: 3377–3381. (ASE 2026 Tools and Datasets, CCF A)
    DOI, Video, Code
  8. Junjie Hu, Cheng Wen, Bin Yu, Jialun Cao, Dugang Liu, Weidi Sun, Haokun Li, Shengchao Qin, Cong Tian.
    ACSLBench: A Verified C/ACSL Corpus and Benchmark with Compositional Call Chains for Formal Specification Synthesis.
    Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering. 2026: 3522–3526. (ASE 2026 Tools and Datasets, CCF A)
    DOI, Video, DataSet
  9. Yuchen Zhang, Cheng Wen, Jialun Cao, Dugang Liu, Zhiwu Xu, Yuwei Liu, Shengchao Qin.
    VerusSeek: Retrieval-Augmented LLM-Based Proof Synthesis for Rust Programs.
    Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering. 2026: 3402–3406. (ASE 2026 Tools and Datasets, CCF A)
    DOI, Video, Code
  10. Lianhe Hu, Cheng Wen, Dugang Liu, Zhiwu Xu, Zhuohua Li, Jie Su, Bin Yu, Shengchao Qin.
    NL2VBench: A Benchmark for End-to-End Natural-Language to Verifiable Rust Generation.
    Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering. 2026: 3478–3482. (ASE 2026 Tools and Datasets, CCF A)
    DOI, Video, DataSet
  11. Cheng Wen, jianheng Li, Jie Su, Bin Yu, Shengchao Qin, Cong Tian, Xiaofeng Li.
    Verihar: A Portable Verification Harness Framework for Aerospace Software IP Across Heterogeneous Backends.
    Proceedings of the 17th International Conference on Reliability, Maintainability, and Safety. 2026. (ICRMS 2026)
    Best Paper Award
  12. Jianheng Li, Cheng Wen, Jie Su, Zhi Ma, Bin Yu, Cong Tian, Shengchao Qin, Xiaofeng Li.
    A Tiered Certification Framework for Trustworthy Reuse of Aerospace Embedded Software IP.
    Proceedings of the 17th International Conference on Reliability, Maintainability, and Safety. 2026. (ICRMS 2026, corresponding author)
  13. Yuandao Cai, Wensheng Tang, Cheng Wen, Shengchao Qin.
    Ghost in the agent: Redefining information flow tracking for llm agents.
    arXiv preprint arXiv:2604.23374, 2026.
    DOI
  14. Chao Jiang, Ding Wang, Dugang Liu, Zhiwu Xu, Cheng Wen, Zhong Ming, Yuwei Liu, Xinyi Wan, Lin Huang.
    StarVerus: LLM-Powered Multi-Agent Collaboration for Industrial Rust Code Verification Automation.
    Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Vol. 2, 2026: 7444–7455. (KDD 2026 Applied Data Science Track, CCF A)
    DOI
  15. Zhuohua Li, Maoli Liu, Yuwen Huang, Cheng Wen, Jie Su, Cong Tian, Shengchao Qin, John C. S. Lui.
    Near-Optimal Learning in Parametric Bandits with Action-Dependent Coarsened Feedback.
    Proceedings of the 40th Annual Conference on Neural Information Processing Systems. 2026. (NeurIPS 2026, CCF A)
  16. Wenjie Wu, Junjie Hu, Cheng Wen, Jialun Cao, Dugang Liu, Zhiwu Xu, Weidi Sun, Haokun Li, Shengchao Qin.
    Spec-Skill: A Pluggable Coding-Agent Plugin for Neuro-symbolic Program Specification Synthesis.
    Companion Proceedings of the 2026 ACM SIGPLAN International Conference on Systems, Programming, Languages, and Applications: Software for Humanity. 2026: 102–107. (SPLASH/ISSTA 2026 Tool Demo, CCF A)
    DOI
  17. Quanhe Wang, Cheng Wen, Dugang Liu, Xingjian Han, Bin Yu, Ping Chen, Shengchao Qin, Cong Tian.
    An Empirical Study of Problem-Aligned Multilingual Code Generation and Directed Code Translation by Large Language Models.
    Proceedings of the 20th International Symposium on Empirical Software Engineering and Measurement. LIPIcs, vol. 394, 2026: 25:1–25:21. (ESEM 2026, CCF B, corresponding author)
    DOI, Slides
  18. Quanhe Wang, Xiangyun Zhang, Cheng Wen, Bin Yu, Ping Chen, Xingjian Han, Shengchao Qin.
    A Direction-Aware Study of LLM-Based Code Translation Across Eight Programming Languages.
    Proceedings of the 20th International Symposium on Empirical Software Engineering and Measurement. LIPIcs, vol. 394, 2026: 63:1–63:14. (ESEM 2026 Emerging Results Track, CCF B, corresponding author)
    DOI, Video
  19. Cheng Wen, Haijun Wang, Zhang X, Xie W, Hua Zheng, Shengchao Qin, Cong Tian.
    Adapting Lightweight Large Language Models for Code Generation and Translation Through Multilingual Solution Pairing.
    Proceedings of the 13th International Conference on Cyber Security and Cloud Computing. IEEE, 2026. (CSCloud 2026, CCF C)
  20. Hua Zheng, Cheng Wen, Muhammad Sadiq, Kuanishbay Sadatdiynov, Durad M, Shengchao Qin.
    TermiRank: Synthesizing Ranking Functions with Large Language Models and Deductive Verification.
    Proceedings of the 13th International Conference on Cyber Security and Cloud Computing. IEEE, 2026. (CSCloud 2026, CCF C)
  21. Xiangyun Zheng, Xuxuan Kuang, Cheng Wen, Bin Yu, Shengchao Qin.
    From Natural Language Requirements to Temporal Logic Specifications with LLMs: A Survey.
    Proceedings of the 13th International Conference on Cyber Security and Cloud Computing. IEEE, 2026. (CSCloud 2026, CCF C)
  22. Hua Zheng, Cheng Wen, Liang K, Muhammad Sadiq, Kuanishbay Sadatdiynov, Aldhahri E.
    SPORK-RL: Cost-Aware Reinforcement Learning for Adaptive Speculative Forking of Tool-Using LLM Agents.
    Proceedings of the 13th International Conference on Cyber Security and Cloud Computing. IEEE, 2026. (CSCloud 2026, CCF C)
  23. Lianhe Hu, Cheng Wen, Jialun Cao, Shengchao Qin, Dugang Liu, Zhiwu Xu, Zhuohua Li, Haokun Li, Weidi Sun.
    Toward Verified Code from Natural Language: Understanding Pipeline Design for Formally Verified Rust Program Generation.
    Proceedings of the 37th International Symposium on Software Reliability Engineering. 2026. (ISSRE 2026, CCF B, corresponding author)
  24. Xiangyun Zhang, Wensheng Wang, Cheng Wen, Shengchao Qin.
    Conservative Hybrid SQL Rewriting with Rules, Retrieval, and LLM Reasoning.
    Proceedings of the 35th ACM International Conference on Information and Knowledge Management. 2026. (CIKM 2026, CCF B, corresponding author)
    DOI
  25. Jiacheng Jiang, Cheng Wen, Zhiyuan Fu, Shengchao Qin.
    CtxFuzz: Discovering Heap-based Memory Vulnerabilities Through Context Heap Operation Sequence Guided Fuzzing.
    Science of Computer Programming, 2026, 249: 103395. (SCP 2026, CCF B, corresponding author)
    PDF, DOI, Code
  26. Junjie Huang, Cheng Wen, Jie Su, Zhiwu Xu, Bin Yu, Shengchao Qin, Cong Tian.
    Preserving Concurrency-Revealing Seeds in Fuzzing of Concurrent Programs via Tuple-Based Coverage Evaluation.
    Proceedings of the 33rd IEEE International Conference on Software Analysis, Evolution and Reengineering. IEEE, 2026: 826–831. (SANER 2026 ERA Track, CCF B, corresponding author)
    DOI,
  27. Yin Wang, Jie Su, Cheng Wen, Rong Wang, Cong Tian, Zhenhua Duan, Shengchao Qin.
    Synergizing LLM-Driven Semantic Reasoning with Assertion-Guided Analysis for Enhanced Vulnerability Detection.
    Proceedings of the 33rd IEEE International Conference on Software Analysis, Evolution and Reengineering. IEEE, 2026: 826–831. (SANER 2026 ERA Track, CCF B)
    DOI
  28. Yajia Lin, Jie Su, Cheng Wen, Rong Wang, Cong Tian, Zhenhua Duan, Shengchao Qin.
    How Well Does Knowledge Injection Enhance LLM-aided Formal Protocol Modeling?
    Proceedings of the 33rd IEEE International Conference on Software Analysis, Evolution and Reengineering. IEEE, 2026: 882–887. (SANER 2026 ERA Track, CCF B)
    DOI
  29. Yuchen Zhang, Cheng Wen, Zhiwu Xu, Dugang Liu, Jialun Cao, Yuwei Liu, Shengchao Qin, Cong Tian.
    Enhancing LLM-based Proof Synthesis for Rust Programs via Semantic Chunking and Hierarchical Context Expansion.
    Proceedings of the 20th Theoretical Aspects of Software Engineering Conference. Cham: Springer Nature Switzerland, 2026: 81–100. (TASE 2026, CCF C, corresponding author)
    DOI, Code
  30. Jun Zhang, Xinyin Liao, Cheng Wen, Jie Su, Zhuohua Li, Yuandao Cai, Xiaoxue Ma, Shengchao Qin.
    Towards Accurate Thread Sharing Analysis via Synchronization-Aware Dynamic Tracing.
    Proceedings of the 20th Theoretical Aspects of Software Engineering Conference. Cham: Springer Nature Switzerland, 2026: 101–120. (TASE 2026, CCF C, corresponding author)
    DOI, Code
  31. Mingyu Wang, Bin Yu, Wenjian Lu, Kefeng Gao, Zhi Wang, Cheng Wen, Xu Lu, Cong Tian.
    DevGen: Automated Generation of Virtual Device Models for Kernel Drivers via Large Language Models.
    Companion Proceedings of the 34th ACM International Conference on the Foundations of Software Engineering. 2026: 1242–1246. (FSE 2026 IVR, CCF A)
    PDF, DOI
  32. Zixuan Yuan, Bin Yu, Xu Lu, Wensheng Wang, Yuanzhe Liu, Cheng Wen, Meng Wang, Chu Chen.
    IDPVerifier: Verifying Interrupt-driven Programs Efficiently via Heuristic and Reduced Partial-order Constraints.
    Companion Proceedings of the 34th ACM International Conference on the Foundations of Software Engineering. 2026: 1237–1241. (FSE 2026 IVR, CCF A)
    PDF, DOI
  33. Yuanzhe Liu, Bin Yu, Ruixue Li, Cheng Wen, Xu Lu, Chu Chen, Cong Tian.
    Atomicity Violation Detection for Interrupt-Driven Programs via Incrementally Exploring Concurrent Paths.
    Proceedings of the IEEE/ACM 48th International Conference on Software Engineering. 2026: 176–180. (ICSE 2026 NIER, CCF A)
    PDF, DOI
  34. 胡俊杰, 陈宇杰, 胡义坤, 文成*, 曹嘉伦, 马智, 苏杰, 孙纬地, 田聪, 秦胜潮.
    大模型驱动的形式化定理证明：综述与展望.
    计算机科学, 2026, 53(4): 1–23. (计算机科学, CCF Chinese T2, corresponding author)
    PDF, DOI
  35. Wenjie Wu, Cheng Wen, Shengchao Qin, Jie Su, Bin Yu, Dugang Liu, Zhiwu Xu, Weidi Sun, Cong Tian.
    LLM-Generated Separation Logic Specifications for Heap-Manipulating Programs: Are We There Yet?
    Proceedings of the 12th International Symposium on Dependable Software Engineering, Theories, Tools and Applications. 2026. (SETTA 2026, CCF C, corresponding author)
  36. Xinyin Liao, Zhiwei Lin, Cheng Wen, Jie Su, Shengchao Qin, Xiaoxue Ma, Xiaofeng Li, Cong Tian.
    Generative Reasoning vs. Conventional Analysis: How Well Do LLMs Detect Data Races in Concurrent Programs?
    Proceedings of the 17th International Conference on Internetware. 2026. (Internetware 2026, CCF C, corresponding author)
  37. Cheng Wen, Yuandao Cai, Hua Zheng, Bin Yu, Dugang Liu, Kuanishbay Sadatdiynov, Zhiwu Xu, Shengchao Qin.
    A Survey on Static Code Analysis with Large Language Models.
    Knowledge Science, Engineering and Management — KSEM 2026 Workshops. 2026. (KSEM Workshop 2026, CCF C, first author)
  38. Junjie Hu, Cheng Wen, Jialun Cao, Yikun Hu, Dugang Liu, Zhi Ma, Zhiwu Xu, Shengchao Qin.
    When Large Language Models Meet Formal Theorem Proving: A Survey.
    Knowledge Science, Engineering and Management — KSEM 2026 Workshops. 2026. (KSEM Workshop 2026, CCF C, corresponding author)
  39. Chao Jiang, Dugang Liu, Cheng Wen, Zhiwu Xu, Hua Zheng, Muhammad Sadiq, Jawwad Ahmed Shamsi, Shengchao Qin, Zhong Ming.
    Large Language Models for Multilingual Code Intelligence: A Survey.
    Knowledge Science, Engineering and Management — KSEM 2026 Workshops. 2026. (KSEM Workshop 2026, CCF C)
    PDF
  40. Jun Zhang, Cheng Wen, Jie Su, Bin Yu, Yuandao Cai, Xiaoxue Ma, Mengda He, Shengchao Qin.
    DtTsa: A Dynamic Thread-Sharing Analysis Tool for Multithreaded Programs.
    Proceedings of the 42nd IEEE International Conference on Software Maintenance and Evolution. IEEE, 2026. (ICSME 2026 Tool Demonstration, CCF B, corresponding author)
    PDF, Video, Code
  41. Cheng Wen, Hua Zheng, Yuhang Guo, Muhammad Sadiq, et al.
    Security Risks in Autonomous AI Agents: A Survey of Threats, Attack Surfaces, and Defenses.
    Proceedings of the 23rd CCF Conference on Web Information Systems and Applications. Singapore: Springer Nature Singapore, 2026. (WISA 2026, CCF C)
  42. Cheng Wen, Zhiwei Lin, Jie Su, Hua Zheng, Han Xingjian, Ping Chen, Shengchao Qin.
    LLM-Assisted Concurrent Unit Test Synthesis Guided by Static Shared-Memory Analysis.
    Proceedings of the 8th International Conference on Blockchain, Artificial Intelligence, and Trustworthy Systems. Singapore: Springer Nature Singapore, 2026. (BlockSys 2026, CCF C)
  43. Zhiwei Lin, Cheng Wen, Jiaxin Xi, Yuandao Cai, Bin Yu, Shengchao Qin.
    From Coverage to Cognition: A Survey of LLM-Assisted and Agentic Fuzzing.
    Proceedings of the 8th International Conference on Blockchain, Artificial Intelligence, and Trustworthy Systems. Singapore: Springer Nature Singapore, 2026. (BlockSys 2026, CCF C, corresponding author)
  44. Jiaxin Xi, Zhiwei Lin, Cheng Wen, Zhuohua Li, Jie Su, Yuandao Cai, Xiaoxue Ma, Shengchao Qin.
    Speed, Space, and Safety: A Multi-Dimensional Empirical Study of Optimized AddressSanitizer.
    Proceedings of the 8th International Conference on Blockchain, Artificial Intelligence, and Trustworthy Systems. Singapore: Springer Nature Singapore, 2026. (BlockSys 2026, CCF C, corresponding author)
  45. Hua Zheng, Yuhang Guo, Cheng Wen, Kuanishbay Sadatdiynov, Mahmud M, Durad M.
    Large Language Models for Omics-Based Disease Classification: A Survey.
    Proceedings of the 20th International Conference on Bioinformatics and Biomedicine. IEEE, 2026. (BIBM 2026 Workshop, CCF B, corresponding author)
  46. Hua Zheng, Huang F, Cheng Wen, Muhammad Sadiq, Mahmud M, Kuanishbay Sadatdiynov, Aldhahri E.
    From Protein Language Models to Biological Discovery: A Critical Survey of Evidence and Evaluation.
    Proceedings of the 20th International Conference on Bioinformatics and Biomedicine. IEEE, 2026. (BIBM 2026 Workshop, CCF B, corresponding author)
  47. Cheng Wen, Wenjun Ke, Muhammad Sadiq, Hua Zheng, Shengchao Qin.
    From Biological Questions to Computation Tree Logic: Structure-Aware Translation with LLMs.
    Proceedings of the 20th International Conference on Bioinformatics and Biomedicine. IEEE, 2026. (BIBM 2026 Poster, CCF B)
  48. Cheng Wen, Kangshuo Yu, Dugang Liu, Bin Yu, Zhi Ma, Zhiwu Xu, Shengchao Qin, Cong Tian.
    Keeping Software Knowledge Alive: Toward Shared Semantic Views for Human-Agent Software Evolution.
    Proceedings of the 26th IEEE International Conference on Data Mining Workshops. IEEE, 2026. (ICDM 2026 Blue Sky, CCF B)
  49. Kangshuo Yu, Xingjian Han, Han Liao, Cheng Wen, Cong Tian, Shengchao Qin, Ping Chen.
    Mining Evidence-Linked Claims from Software Repositories for Contradiction-Aware Knowledge Diagnosis.
    Proceedings of the 26th IEEE International Conference on Data Mining Workshops. IEEE, 2026. (ICDM 2026 Blue Sky, CCF B)
  50. Hua Zheng, Yuhang Guo, Kuanishbay Sadatdiynov, Cheng Wen, Muhammad Sadiq, Dugang Liu, Jawwad Ahmed Shamsi, Anam Qureshi.
    From Heuristics to Transformers: A Comprehensive Survey of Type Inference from Stripped Binaries.
    Proceedings of the 2026 6th International Conference on Computer Network Security and Software Engineering. 2026: 204–211. (CNSSE 2026, corresponding author)
    DOI
  51. Shaolin Zhang, Hongjin Liu, Zhi Ma, Xiao Liang, Cheng Wen.
    Formal Verification of Aerospace Software IP Components: A Multi-Tool Case Study.
    Proceedings of the 2026 6th International Conference on Computer Network Security and Software Engineering. 2026: 219–228. (CNSSE 2026)
    DOI
  52. Hua Zheng, Yuhang Guo, Cheng Wen, Kuanishbay Sadatdiynov, Muhammad Sadiq, Durad M.
    Toward Autonomous AI Agents for Protein Dark Matter Discovery: A Survey of Enabling Tools, Agentic Workflows, and Validation Principles.
    Proceedings of the 10th International Conference on Smart Computing and Communication. Cham: Springer International Publishing, 2026. (SmartCom 2026, corresponding author)
    Video,
  53. Hua Zheng, Cheng Wen, Muhammad Sadiq, Kuanishbay Sadatdiynov, Jawwad Ahmed Shamsi.
    Harness Engineering for AI Coding Agents: Emerging Practices and Principles.
    Proceedings of the 10th International Conference on Electronic Information Technology and Computer Engineering. IEEE, 2026: 609–614. (EITCE 2026, corresponding author)
    DOI
  54. Cheng Wen, Quanhe Wang, Yuhang Guo, et al.
    Trustworthy Programming Language Translation with Large Language Models: A Focused Review.
    Proceedings of the 3rd World Conference on Computer and Information Security. IEEE, 2026: 208–212. (WCCIS 2026)
    DOI
  55. Yuhang Guo, Cheng Wen, Hua Zheng.
    From Context to Action: Security Risks and Defensive Directions for Autonomous AI Agents.
    Proceedings of the Asia-Pacific Conference on Artificial Intelligence and Machine Learning. 2026. (APAM 2026, corresponding author)
    DOI
  56. Yitong, Zhuohua Li, Cheng Wen, Shiyuan Yu, Jie Su, Jianhao He, Shengchao Qin.
    When Large Language Models Meet Quantum Programming: A Review.
    Proceedings of the 5th Quantum Computation Conference. Singapore: Springer Nature Singapore, 2026. (CQCC 2026, corresponding author)

2025

  1. Zhi Ma, Cheng Wen, Zhexin Su, Xiao Liang, Cong Tian, Shengchao Qin, Mengfei Yang.
    Bridging Natural Language and Formal Specification - Automated Translation of Software Requirements to LTL via Hierarchical Semantics Decomposition Using LLMs.
    Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering. 2025: 1208–1220. (ASE 2025, CCF A)
    ACM SIGSOFT Distinguished Paper Award at ASE 2025
    PDF, DOI
  2. Jialun Cao, Yaojie Lu, Meiziniu Li, Haoyang Ma, Haokun Li, Mengda He, Cheng Wen, Le Sun, Hongyu Zhang, Shengchao Qin, Shing-Chi Cheung, Cong Tian.
    From Informal to Formal - Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal Proofs.
    Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025: 26984–27003. (ACL 2025, CCF A)
    PDF, DOI, DataSet1, DataSet2, Model
  3. Zhi Ma, Cheng Wen, Bin Yu, Jie Su.
    Integrating Ensemble Learning and Large Language Models for Efficient Formal Verification of IP-Based Aerospace Systems.
    Accepted by Information Fusion (INFFUS 2025). Available online 8 July 2025, 103466.
    PDF, DOI
  4. GuoHua Xin, Guangquan Xu, Yao Zhang, Cheng Wen, Cen Zhang, Xiaofei Xie, Neal N. Xiong, Shaoying Liu, Pan Gao.
    IRHunter: Universal Detection of Instruction Reordering Vulnerabilities for Enhanced Concurrency in Distributed and Parallel Systems.
    IEEE Transactions on Parallel and Distributed Systems, 2025, 36(6): 1220–1236. (TPDS 2025, CCF A, CAS Q1)
    PDF, DOI
  5. Jie Su, Liansai Deng, Cheng Wen, et al.
    MFH: A Multi-faceted Heuristic Algorithm Selection Approach for Software Verification.
    arXiv preprint arXiv:2503.22228, 2025.
    DOI

2024

  1. Cheng Wen, Jialun Cao, Jie Su, Zhiwu Xu, Shengchao Qin, Mengda He, Haokun Li, Shing-Chi Cheung, Cong Tian.
    Enchanting Program Specification Synthesis by Large Language Models using Static Analysis and Program Verification.
    Proceedings of the 36th International Conference on Computer Aided Verification. LNCS, vol. 14682, 2024: 302–328. (CAV 2024, CCF A)
    Learn more at https://sites.google.com/view/autospecification/
    PDF, DOI, Code
  2. Zhiwu Xu, Bohao Wu, Cheng Wen, Bin Zhang, Shengchao Qin, Mengda He.
    RPG: Rust Library Fuzzing with Pool-based Fuzz Target Generation and Generic Support.
    Proceedings of the 46th International Conference on Software Engineering. 2024: 124:1–124:13. (ICSE 2024, CCF A, corresponding author)
    ICSE'24 Artifact Evaluation Committee awarded available badge for RPG!
    Learn more at https://sites.google.com/view/rust-rpg/
    PDF, DOI, Code
  3. Cheng Wen, Yuandao Cai, Bin Zhang, Jie Su, Zhiwu Xu, Dugang Liu, Shengchao Qin, Zhong Ming, Cong Tian.
    Automatically Inspecting Thousands of Static Bug Warnings with Large Language Model: How Far Are We?
    ACM Transactions on Knowledge Discovery from Data, 2024, 18(7): 168:1–168:34. (TKDD 2024, CCF B)
    PDF, DOI, Code
  4. Jie Su, Liansai Deng, Cheng Wen, Shengchao Qin and Cong Tian.
    CFStra: Enhancing Configurable Program Analysis Through LLM-driven Strategy Selection Based on Code Features.
    Proceedings of the 18th Theoretical Aspects of Software Engineering Conference. 2024: 374–391. (TASE 2024, CCF C)
    PDF, DOI, Code
  5. Jiacheng Jiang, Cheng Wen, Shengchao Qin.
    CtxFuzz: Discovering Heap-based Memory Vulnerabilities Through Context Heap Operation Sequence Guided Fuzzing.
    Proceedings of the 18th Theoretical Aspects of Software Engineering Conference. 2024: 205–223. (TASE 2024, CCF C, corresponding author)
    PDF, DOI, Code
  6. Zhiyuan Fu, Jiacheng Jiang, Cheng Wen, Zhiwu Xu, Shengchao Qin.
    MemSpate: Memory Usage Protocol Guided Fuzzing.
    Proceedings of the 25th International Conference on Formal Engineering Methods. Singapore: Springer Nature Singapore, 2024: 237–256. (ICFEM 2024, CCF C)
    PDF, DOI
  7. Zhi Ma, Cheng Wen, Jie Su, Ming Zhao, Bin Yu, Xu Lu, Cong Tian.
    Towards Practical Requirement Analysis and Verification: A Case Study on Software IP Components in Aerospace Embedded Systems.
    arXiv preprint arXiv:2404.00795, 2024.
    PDF, DOI

2022

  1. Cheng Wen, Mengda He, Bohao Wu, Zhiwu Xu and Shengchao Qin.
    Controlled Concurrency Testing via Periodical Scheduling.
    Proceedings of the 44th International Conference on Software Engineering. 2022: 474–486. (ICSE 2022, CCF A)
    ICSE'22 Artifact Evaluation Committee awarded reusable badge and available badge for PERIOD!
    Learn more at https://sites.google.com/view/period-cct/
    PDF, DOI, Slides, DataSet, Video, Code

2021

  1. Zhiwu Xu, Cheng Wen, Shengchao Qin and Mengda He.
    Extracting automata from neural networks using active learning.
    PeerJ Computer Science, 2021, 7: e436. (PeerJCS 2021, JCR Q2)
    PDF, DOI

2020

  1. Cheng Wen, Haijun Wang, Yuekang Li, Shengchao Qin, Yang Liu, Zhiwu Xu, Hongxu Chen, Xiaofei Xie, Geguang Pu and Ting Liu.
    MemLock: Memory Usage Guided Fuzzing.
    Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering. 2020: 765–777. (ICSE 2020, CCF A)
    ICSE'20 Artifact Evaluation Committee awarded reusable badge and available badge for MemLock!
    Learn more at https://wcventure.github.io/MemLock/
    PDF, DOI, Slides, DataSet, Video, Code
  2. Haijun Wang, Xiaofei Xie, Yi Li, Cheng Wen, Yang Liu, Shengchao Qin, Hongxu Chen and Yulei Sui.
    Typestate-Guided Fuzzer for Discovering Use-after-Free Vulnerabilities.
    Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering. 2020: 999–1010. (ICSE 2020, CCF A)
    Learn more at https://sites.google.com/view/uafl/
    PDF, DOI, Slides, DataSet, Video

2019

  1. Zhiwu Xu, Cheng Wen, and Shengchao Qin.
    Type Learning for Binaries and its Applications.
    IEEE Transactions on Reliability, 2019, 68(3): 893–912. (IEEE T RELIAB 2019, CCF B, CAS Q2)
    PDF, DOI, Slides, DataSet, Code

2018

  1. Zhiwu Xu, Xiongya Hu, Cheng Wen, and Shengchao Qin.
    Extracting Automata from Neural Networks Using Active Learning.
    National Conference on Formal Methods and Applications. Chongqing, China. November 3–4, 2018. (FMAC 2018)
    Best Paper Award
    PDF, DOI
  2. Zhiwu Xu, Cheng Wen, and Shengchao Qin.
    State-taint analysis for detecting resource bugs.
    Science of Computer Programming, 2018, 162: 93–109. (SCP 2018, CCF B)
    PDF, DOI

2017

  1. Zhiwu Xu, Cheng Wen, Shengchao Qin and Zhong Ming.
    Effective malware detection based on behaviour and data features.
    Proceedings of the 2nd International Conference on Smart Computing and Communication (SmartCom 2017). LNCS, vol. 10699, 2018: 53–66. (SmartCom 2017)
    Best Student Paper Award
    PDF, DOI, Slides, Code
  2. Zhiwu Xu, Cheng Wen, and Shengchao Qin.
    Learning types for binaries.
    Proceedings of the 19th International Conference on Formal Engineering Methods. Cham: Springer International Publishing, 2017: 430–446. (ICFEM 2017, CCF C)
    PDF, DOI, Slides, DataSet, Code

Awards and Honors

  • 2026: Outstanding Young Scholar Award in Asia-Pacific AI Education (2026亚太人工智能教育优秀青年学者奖).
  • 2026: Highlight Paper, the 25th China National Conference on Computational Linguistics (CCL 2026).
  • 2026: Best Paper Award, the 17th International Conference on Reliability, Maintainability, and Safety (ICRMS 2026).
  • 2025: ACM SIGSOFT Distinguished Paper Award (ASE 2025).
  • 2024: Outstanding Teacher Award (2023–2024年度优秀教师), Guangzhou Institute of Technology, Xidian University.
  • 2020: National Scholarship (国家奖学金).
  • 2018: Best Paper Award, National Conference on Formal Methods and Applications (FMAC 2018).
  • 2017: Best Student Paper Award, SmartCom 2017.
  • 2017: Outstanding Graduate Student, Shenzhen University.

Teaching, Patents & Software Copyrights

Teaching and Education Publications

  1. 文成, 秦胜潮*, 刘杜钢, 许智武. AI时代程序分析与验证类课程的前沿化、实践化与过程化重构. 计算机技术与教育学报, 2027.
  2. 郑华, 文成*. 大语言模型赋能OBE理念下人工智能导论课程教学改革研究. 计算机技术与教育学报, 2027.
  3. 文成, 于斌, 苏杰, 秦胜潮*. 面向智能软件开发能力培养的编译原理课程价值重构与内容优化探析. 计算机应用文摘, 2027.

Chinese Patent Applications

  1. 文成, 刘杜钢, 胡联合, 蒋超, 许智武, 秦胜潮. 面向 Rust 形式化验证的上下文感知错误选择与修复轨迹优化方法和装置. CN202610861014.5
  2. 文成,,胡俊杰, 杨超华, 刘杜钢, 许智武, 秦胜潮. 面向 Rust 形式化验证的上下文感知错误选择与修复轨迹优化方法和装置. CN202611091462.8
  3. 张雨晨, 文成, 刘杜钢, 许志武, 秦胜潮. 一种面向 Rust/Verus 程序的自动化形式化证明生成方法、装置及系统. CN202610889073.3
  4. 林志伟, 廖欣茵, 文成, 苏杰, 秦胜潮. 基于多步智能体的应用程序分析方法、装置、设备及介质. CN202611258618
  5. 张俊, 文成, 苏杰, 秦胜潮. 一种面向多线程程序的动态线程共享分析方法及设备. CN202610919302.1
  6. 黄俊杰, 文成, 苏杰, 秦胜潮. 一种基于线程并发二元关系覆盖的模糊测试方法. CN202610287939.3
  7. 王颖, 苏杰, 文成, 田聪, 段振华. 融合大模型语义推理的断言导向漏洞检测方法. CN202610073326X
  8. 马智, 文成, 梁潇, 柯汶君, 王小兵, 田聪, 秦胜潮, 杨孟飞. 语句转换方法、装置、电子设备以及存储介质. CN202511775475.2
  9. 文成, 苏杰, 黄俊杰, 周润博. 一种面向C/C++并发程序库的测试用例生成方法. CN2025108112588
  10. 于斌, 王明煜, 鲁文健, 王志, 高科峰, 文成, 陆旭, 王文胜, 苏镇镇, 田聪. 一种基于大语言模型引导的内核驱动虚拟设备生成与模糊测试方法. CN202610168967.3
  11. 于康朔, 苏杰, 文成, 田聪. 基于领域特征图与数据流约束的测试脚本自动生成方法. CN202610571957.4
  12. 于康朔, 苏杰, 文成, 田聪. 基于语义中间表示与分层检索增强的嵌入式软件测试脚本自动生成方法. CN202610571950.2
  13. 邓联赛, 苏杰, 田聪, 文成, 秦胜潮. 软件验证算法预测方法和装置、电子设备、存储介质. CN2025110427270

Software Copyrights

  1. 柯汶君, 文成, 马智, 秦胜潮. 大模型辅助自然语言描述转化时序逻辑规约生成软件 [简称：TLCrafter] V1.0（登记号：2026SR1036507）
  2. 于康朔, 苏杰, 文成, 田聪. 基于大模型的领域软件智能化测试用例生成软件 V1.0（登记号：2026SR0804879）
  3. 林志伟, 文成, 秦胜潮, 蔡源稻. 基于可扩展标签对比和存储结构优化的轻量级内存错误检测软件 [简称：LMSan] V1.0 (登记号：2025SR2553076)
  4. 王颖, 苏杰, 文成. 协同LLM语义推理的程序路径约束生成与漏洞分析软件（申请中）
  5. 邓联赛, 苏杰, 文成. 基于代码特征的大语言模型驱动策略选择增强可配置程序分析软件（申请中）
  6. 邓联赛, 苏杰, 文成. 基于间接标记的软件验证分步算法的智能选择软件（申请中）

  Practical Security Impact

  I have found several security-critical vulnerabilities in widely used open-source projects and libraries, such as Bintuils, Elfutils, Libtiff, Binaryen, NASM, MJS, etc.

CVEs List (83 CVEs)

CVE ID Package Vulnerability Type CVE ID Package Vulnerability Type
CVE-2023-49558 Yasm 9defefa NULL pointer dereference
CVE-2023-49557 Yasm 9defefa NULL pointer dereference CVE-2023-49556 Yasm 9defefa Heap Buffer Overflow
CVE-2023-49555 Yasm 9defefa NULL pointer dereference CVE-2023-49554 Yasm 9defefa Use-after-free
CVE-2023-49553 mJS 2.20.0 NULL pointer dereference CVE-2023-49552 mJS 2.20.0 Stack Overflow
CVE-2023-49551 mJS 2.20.0 NULL pointer dereference CVE-2023-49550 mJS 2.20.0 NULL pointer dereference
CVE-2023-49549 mJS 2.20.0 NULL pointer dereference CVE-2022-26291 Lrzip v0.641 Concurrency Use-after-free
CVE-2020-36375 MJS 1.20.1 Stack Overflow CVE-2020-36374 MJS 1.20.1 Stack Overflow
CVE-2020-36373 MJS 1.20.1 Stack Overflow CVE-2020-36372 MJS 1.20.1 Stack Overflow
CVE-2020-36371 MJS 1.20.1 Stack Overflow CVE-2020-36370 MJS 1.20.1 Stack Overflow
CVE-2020-36369 MJS 1.20.1 Stack Overflow CVE-2020-36368 MJS 1.20.1 Stack Overflow
CVE-2020-36367 MJS 1.20.1 Stack Overflow CVE-2020-36366 MJS 1.20.1 Stack Overflow
CVE-2020-18900 libyal libexe 20181128 Heap Buffer Overflow CVE-2020-18897 libyal Libpff before 20180623 Use-after-free
CVE-2020-18899 Exiv2 0.27 Uncontrolled Memory Allocation CVE-2020-18898 Exiv2 0.27 Stack Overflow
CVE-2020-18395 GNU Gama 2.04 NULL Pointer Dereference CVE-2020-18392 MJS 1.20.1 Stack Overflow
CVE-2020-18382 Binaryen 1.38.25 NULL Pointer Dereference CVE-2020-18378 Binaryen 1.38.26 Heap Buffer Overflow
CVE-2019-16166 GNU cflow 1.6 Heap Buffer Overflow CVE-2019-16165 GNU cflow 1.6 Use-after-free
CVE-2019-15140 ImageMagick 7.0.8-43 Use-after-free CVE-2019-11471 Libheif v1.4.0 Use-after-free
CVE-2019-7704 Binaryen 1.38.22 Uncontrolled Memory Allocation CVE-2019-7703 Binaryen 1.38.22 Use-after-free
CVE-2019-7702 Binaryen 1.38.22 NULL pointer dereference CVE-2019-7701 Binaryen 1.38.22 Heap Buffer Overflow
CVE-2019-7700 Binaryen 1.38.22 Heap Buffer Overflow CVE-2019-7699 Bento4 v1.5.1-627 Heap Buffer Overflow
CVE-2019-7698 Bento4 v1.5.1-627 Uncontrolled Memory Allocation CVE-2019-7697 Bento4 v1.5.1-627 Assertion failed
CVE-2019-7665 Elfutils 0.175 Heap Buffer Overflow CVE-2019-7664 Elfutils 0.175 negative-size in memcpy
CVE-2019-7663 Libtiff 4.0.10 Invalid Address Read CVE-2019-7662 Binaryen 1.38.22 Assertion failed
CVE-2019-7154 Binaryen 1.38.22 Heap Buffer Overflow CVE-2019-7153 Binaryen 1.38.22 NULL pointer dereference
CVE-2019-7152 Binaryen 1.38.22 Heap Buffer Overflow CVE-2019-7151 Binaryen 1.38.22 NULL pointer dereference
CVE-2019-7150 Elfutils 0.175 Unknown Crash CVE-2019-7149 Elfutils 0.175 Heap Buffer Overflow
CVE-2019-7148 Elfutils 0.175 Uncontrolled Memory Allocation CVE-2019-7147 NASM 2.14rc16 Global buffer overflow
CVE-2019-6293 Elfutils 0.175 Heap Buffer Overflow CVE-2019-6293 Flex 2.6.4 Stack Overflow
CVE-2019-6292 Yaml-cpp v0.6.2 Stack Overflow CVE-2019-6291 NASM 2.14.03rc1 Stack Overflow
CVE-2019-6290 NASM 2.14.03rc1 Stack Overflow CVE-2018-20712 Binutils 2.31 Heap Buffer Overflow
CVE-2018-20657 Binutils 2.31 Memory Leak CVE-2018-20652 Tinyexr v0.9.5 Uncontrolled Memory Allocation
CVE-2018-20651 Binutils 2.31 Invalid Address Read CVE-2018-20593 Mini Xml v2.1 Stack Buffer Overflow
CVE-2018-20592 Mini Xml v2.1 Use-after-free CVE-2018-20591 libming v0.4.8 Heap Buffer Overflow
CVE-2018-20002 Binutils 2.31 Memory Leak CVE-2018-18701 Binutils 2.31 Stack Overflow
CVE-2018-18700 Binutils 2.31 Stack Overflow CVE-2018-18607 Binutils 2.31 NULL Pointer Dereference
CVE-2018-18606 Binutils 2.31 NULL Pointer Dereference CVE-2018-18605 Binutils 2.31 Heap Buffer Overflow
CVE-2018-18521 Elfutils 0.174 Divide-by-zero CVE-2018-18520 Elfutils 0.174 Invalid Address Read
CVE-2018-18484 Binutils 2.31 Stack Overflow CVE-2018-18483 Binutils 2.31 Integer overflow
CVE-2018-18310 Elfutils 0.174 Invalid Address Read CVE-2018-18309 Binutils 2.31 Invalid Address Read
CVE-2018-17985 Binutils 2.31 Stack Overflow CVE-2018-17795 LibTIFF 4.0.9 Heap Buffer Overflow
CVE-2018-17794 Binutils 2.31 NULL Pointer Dereference CVE-2018-16403 Elfutils 0.173 Heap Buffer Overflow
CVE-2018-16402 Elfutils 0.173 Double Free CVE-2018-16062 Elfutils 0.173 Heap Buffer Overflow
logo bottom

Copyright © 2020. wcventure All rights reserved. Updated: