Zhou Yang's profile photo

Zhou YANG (杨 洲) [Pronunciation]

Ph.D at Singapore Management University 🇸🇬

The funniest teacher🧑‍🏫 in Jurong West Primary School🇸🇬 (Unofficially nominated by several kids)

M.Sc. from Software System Engineering, University College London 🇬🇧

B.Eng. from School of Information Engineering, Yangzhou University 🇨🇳

An interesting story: Yangzhou graduated from Yangzhou University in Yangzhou City.

About Me [⬆TOP]

I have defended my thesis and am on the job market! Feel free to reach out if you know of any good opportunities!

Singapore Management University

Currently, I am a Senior Research Engineer and doing PhD at SMU. I am a member of Software Analytics Research Group, supervised by Prof. David LO. My main focus is "beyond accuracy of language models of code." I study a broad of properties including robustness, security, privacy, efficiency, fairness and usability of code model ecosystem.

I also have publication records in the general AI testing, including evaluating correctness of ASR systems, fairness of NLP models, security threats in reinforcement learning models, etc.

Our group and I are open to collaboration and communication.

University College London

I was a MSc student at University College London, studying Software System Engineering. My master dissertation is about automated program repair for syntax errors, which is co-supervised by Prof. Earl Barr (UCL) and Prof. Martin Monperrus (KTH).

Yangzhou University

I obtained my bachelor in software engineering from Yangzhou University, China (Yes, very interesting, I have the same name as my university!) I was member of the Elite class of Innovation and Entrepreneurship and selected as the outstanding graduate. At the same time of guaranteeing 1st GPA, I also served as the leader of two university-level student organisations. I had a very enjoyable and memorable time here.

News [⬆TOP]

  • [2024.03] One paper is accepted by IEEE S&P 2024!
  • [2024.01] One paper is accepted by IEEE Transactions on Software Engineering!
  • [2023.10] One paper is accepted by SEIS Track of ICSE 2024! See you in Lisbon!
  • [2023.11] I'm happy to serve as Junior Program Committee in MSR 2024!
  • [2023.10] One paper is accepted by Technical Track of ICSE 2024! See you in Lisbon!
  • [2023.07] 😫My father is diagnosed with cancer. I have to support my family and pause research projects for a while. ⚠️Do take medical screening regularly if you happen to see my webpage.
  • [2023.06] One paper is accepted by Technical Track of ICSME 2023!
  • [2023.06] I recieved SIGSOFT Travel Support from CAPS program. See you in Seattle!
  • [2023.05] One paper is accepted by Technical Track of ISSTA 2023!
  • [2023.04] I gave an invited talk at TU Delft, titled "What's beyond the accuracy of code models?
  • [2023.03] One paper is accepted by Technical Track of MSR 2023! See you in Melbourne!

Selected Publications [Full list] [⬆TOP]

📧 means that I'm the corresponding author.

  1. Hotfixing Large Language Models for Code
    Zhou Yang and David Lo.
    Under review.
  2. Ecosystem of Large Language Models for Code
    Zhou Yang, Jieke, Premkumar Devanbu and David Lo.
    Under review.
  3. Robustness, Security, Privacy, Explainability, Efficiency, and Usability of Large Language Models for Code
    Zhou Yang, Zhensu Sun, Terry Yue Zhuo, Premkumar Devanbu, and David Lo.
    Under review.
  4. Gotcha! This Model Uses My Code! Evaluating Membership Leakage Risks in Code Models
    Zhou Yang, Zhipeng Zhao, Chenyu Wang, Jieke Shi, Dongsun Kim, DongGyun Han, David Lo.
    IEEE Transactions on Software Engineering.
  5. Unveiling Memorization in Code Models
    Zhou Yang, Zhipeng Zhao, Chenyu Wang, Jieke Shi, Dongsun Kim, DongGyun Han, David Lo.
    The 46th International Conference on Software Engineering (ICSE 2024) (13 Pages, Technical Track)
  6. Natural Attack for Pre-trained Models of Code
    Zhou Yang, Jieke Shi, Junda He and David Lo.
    2022 IEEE/ACM 44th International Conference on Software Engineering (ICSE). (12 pages, Technical Track.)
  7. Revisiting Neuron Coverage Metrics and Quality of Deep Neural Networks
    Zhou Yang, Jieke Shi, Muhammad Hilmi Asyrofi and David Lo.
    2022 IEEE 29th International Conference on Software Analysis, Evolution and Reengineering (SANER). (12 pages)
  8. Stealthy Backdoor Attack for Code Models
    Zhou Yang, Bowen Xu, Jie M Zhang, Hong Jin Kang, Jieke Shi, Junda He, David Lo.
    IEEE Transactions on Software Engineering.
  9. Prioritizing Speech Test Cases
    Zhou Yang, Jieke Shi, Hilmi Asyrofi, Bowen Xu, Xin Zhou, DongGyun Han, David Lo.
    ACM Transactions on Software Engineering and Methodology.
  10. What Do Users Ask in Open-Source AI Repositories? An Empirical Study of GitHub Issues
    Zhou Yang, Chenyu Wang, Jieke Shi et al.
    The 20th IEEE International Conference on Mining Software Repositories (MSR 2023) (12 pages, Technical Track.)
  11. BiasRV: Uncovering biased sentiment predictions at runtime
    Zhou Yang, Muhammad Hilmi Asyrofi, David Lo.
    The 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (FSE 2021) (Tool Demo.)
  12. Incbl: Incremental bug localization
    Zhou Yang, Jieke Shi, Shaowei Wang, David Lo.
    The 36th IEEE/ACM International Conference on Automated Software (FSE 2021) (ASE Demo.)
  13. Finding Safety Violations of AI-Enabled Control Systems through the Lens of Synthesized Proxy Programs
    Jieke Shi, Zhou Yang📧, Junda He, Bowen Xu, Dongsun Kim, Donggyun Han, and David Lo.
    ACM Transactions on Software Engineering and Methodology.
  14. Greening Large Language Models of Code
    Jieke Shi, Zhou Yang📧, Hong Jin Kang, Bowen Xu, Junda He, David Lo.
    The 46th IEEE/ACM International Conference on Software Engineering (ICSE) (12 pages, SEIS Track.)
  15. Curiosity-Driven Testing for Sequential Decision-Making Process
    Junda He, Zhou Yang📧, Jieke Shi et al.
    The 46th International Conference on Software Engineering (ICSE 2024) (13 Pages, Technical Track)
  16. Curiosity-Driven and Victim-Aware Adversarial Policies
    Chen Gong, Zhou Yang📧, Yunpeng Bai, et al.
    The Annual Computer Security Applications Conference (ACSAC 2022) (15 pages, Technical Track.)
  17. Compressing Pre-trained Models of Code into 3 MB
    Jieke Shi, Zhou Yang, Bowen Xu, Hong Jin Kang, David Lo
    The 37th IEEE/ACM International Conference on Automated Software Engineering. (ASE 2022) (12 pages, Research Track.)
  18. Efficient and Green Large Language Models for Software Engineering: Vision and the Road Ahead
    Jieke Shi, Zhou Yang, David Lo
    ACM Transactions on Software Engineering and Methodology
  19. Mind Your Data! Hiding Backdoors in Offline Reinforcement Learning Datasets
    Chen Gong, Zhou Yang📧, Yunpeng Bai et al.
    45th IEEE Symposium on Security and Privacy (S&P 2024).
  20. BiasFinder: Metamorphic Test Generation to Uncover Bias for Sentiment Analysis Systems
    Asyrofi Hilmi, Zhou Yang📧, Imam Nur Bani Yusuf, Hong Jin Kang, Ferdian Thung, and David Lo.
    IEEE Transactions on Software Engineering.
  21. Assessing AI Detectors in Identifying AI-Generated Code: Implications for Education
    Wei Hung Pan, Ming Jie Chok, Jonathan Wong, Yung Xin Shin, Yeong Shian Poon, Zhou Yang📧 et al.
    The 46th International Conference on Software Engineering (ICSE 2024)
  22. Synthesizing Speech Test Cases with Text-to-Speech? An Empirical Study on the False Alarms in Automated Speech Recognition Testing
    Julia Lau, Kelvin Kong, Julian Hao Yong, Per Hoong Tan, Zhou Yang📧 et al.
    ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2023)
  23. Adversarial Attacks on Code Models with Discriminative Graph Patterns
    Thanh-Dat Nguyen, Zhou Yang📧, Xuan Bach D Le, David Lo
    Under revision of ACM TOSEM.
  24. AI Coders Are Among Us: Rethinking Programming Language Grammar Towards Efficient Code Generation
    Zhensu Sun, Xiaoning Du, Zhou Yang, Li Li, David Lo
    ISSTA 2024 (13 pages, Technical Track.)
  25. Large Language Models for Software Engineering: A Systematic Literature Review
    Xinyi Hou, Yanjie Zhao, Yue Liu, Zhou Yang, Kailong Wang, Li Li, Xiapu Luo, David Lo, John Grundy, Haoyu Wang.
    ACM Transactions on Software Engineering and Methodology.

Services [⬆TOP]

Journal Reviewing

  • Empirical Software Engineering, 2024-Now
  • Communications of the ACM, 2024-Now
  • IEEE Transactions on Dependable and Secure Computing, 2024-Now
  • Journal of Software: Evolution and Process, 2024-Now
  • IEEE Transactions on Software Engineering, 2023-Now
  • ACM Transactions on Software Engineering and Methodology, 2023-Now
  • Neurocomputing Journal, 2021-Now

Conference Activities

  • Web Co-Chair, ICSE 2025
  • Web Co-Chair, MSR 2022
  • Shadow PC, ICSE 2025
  • PC Member, APSEC 2024
  • PC Member, Internetware 2024
  • PC Member, Forge 2024
  • Junior PC Member, MSR 2024
  • PC Member, ECAI 2023
  • Shadow PC Member, MSR 2022

Awards [⬆TOP]

Student Supervision [⬆TOP]

As a PhD student, my duty is to conduct great research and publish high-quality papers. As a senior research engineer in the group, my duty is to help other research engineers and students thrive and succeed. I'm honored to (co-)supervise the following students:

MOE Tier 3: Understanding how to develop AI systems in practice

  • Chenyu Wang, Research Engineer/PhD Student at SMU, working on understanding the quality assurance practice in industrial AI systems.
  • Yunbo Lyu, Research Engineer/PhD Student at SMU, working on understanding fairness issues in AI systems.
  • Yinan Wu, Research Engineer at NC State University, working on understanding the practice of sharing and reusing AI models.

AI.SG Project: Testing Reinforcement Learning-based Systems

  • Chen Gong Visiting Master Student (now PhD Student at University of Virginia), working on data poisoning for offline reinforcement learning.
  • Junda He Research Engineer/PhD Student at SMU, working on testing reinforcement learning-based systems.
  • Jieke Shi Research Engineer/PhD Student at SMU, working on monitor and verify RL systems at runtime.

MOE Tier 1: Testing and Verification of Artificial Intelligence Systems

  • Muhammad Hilmi Asyrofi Research Engineer (now Data Scientist at PropertyGuru Group), working on testing speech recognition systems and uncovering bias in sentiment analysis systems.

Undergraduate Projects

  • MSc Graduation Project at SMU, evaluating the deprecated API recommended by ChatGPT.
  • 2023 Graduation projects in Monash Malaysia, working on analyzing ChatGPT, publication at ICSE 2024
  • 2022 Graduation projects in Monash Malaysia, publication SANER23, ICST23, ISSTA23
  • Hui Ning Ko (SMU Undergraduate), work on bug localization
  • Harshit Jain (SMU Undergraduate), publication: ICSME21
  • Wei Quan Chu (SMU Undergraduate), publication: ICSME21