Pingchuan Ma

As of 13 June 2025

I am a postdoctoral researcher in the Department of Computer Science and Engineering at the Hong Kong University of Science and Technology (HKUST), supervised by Prof. Shuai Wang, where I also received my Ph.D. Prior to this appointment, I was a visiting scholar at Sky Lab at UC Berkeley, hosted by Prof. Alvin Cheung. I have also worked as Chief AI Scientist at Myko, an AI startup. I received my B.Eng. from the Beijing Electronic Science and Technology Institute. My research interests lie in building intelligent, private and responsible data systems.

I am also the co-founder of CipherInsight Limited, a company I started with Prof. Shuai Wang, focusing on privacy-preserving computation with practical and developer-friendly cryptographic solutions.

I can be reached at pmaab at cse dot ust dot hk.

Publications

† means corresponding author.

Guardrail: Automated Integrity Constraint Synthesis From Noisy Data
Pingchuan Ma, Zhaoyu Wang, Zhenlan Ji, Zongjie Li, Ao Sun, and Shuai Wang
ACM SIGMOD International Conference on Management of Data (SIGMOD ’26)Code
Measuring and Augmenting Large Language Models for Solving Offensive Security Challenges
Zimo Ji, Daoyuan Wu, Wenyuan Jiang, Pingchuan Ma, Zongjie Li, and Shuai Wang
ACM Conference on Computer and Communications Security (CCS 2025)
Causality-Aided Evaluation and Explanation of Large Language Model-based Code Generation
Zhenlan Ji, Pingchuan Ma†, Zongjie Li, Zhaoyu Wang, and Shuai Wang†
ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2025)arXiv
Reeq: Testing and Mitigating Ethically Inconsistent Suggestions of Large Language Models with Reflective Equilibrium
Pingchuan Ma, Zhaoyu Wang (equal contribution), Zongjie Li, Zhenlan Ji, Ao Sun, Juergen Rahmel, and Shuai Wang
ACM Transactions on Software Engineering and Methodology (TOSEM)arXivCode
Algorithms, Applications, and Verification of Causal Structure Learning
Pingchuan Ma
PhD Thesis
SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner
Xunguang Wang, Daoyuan Wu, Zhenlan Ji, Zongjie Li, Pingchuan Ma, Shuai Wang, Yingjiu Li, Yang Liu, Ning Liu, and Juergen Rahmel
The 34th USENIX Security Symposium (USENIX Security 2025)arXivCode
Split and Merge: Aligning Position Biases in LLM-based Evaluators
Zongjie Li, Chaozheng Wang, Pingchuan Ma, Daoyuan Wu, Shuai Wang, Cuiyun Gao, and Yang Liu
The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024 Main)arXiv
Scalable Differentiable Causal Discovery in the Presence of Latent Confounders with Skeleton Posterior
Pingchuan Ma, Rui Ding, Qiang Fu, Jiaru Zhang, Shuai Wang, Shi Han, and Dongmei Zhang
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD ’24)arXivPress (in Chinese)Code
PP-CSA: Practical Privacy-Preserving Software Call Stack Analysis
Zhaoyu Wang, Pingchuan Ma†, Huaijin Wang, and Shuai Wang†
ACM Conference on Object-Oriented Programming, Systems, Languages, and Applications (OOPSLA ’24)Code
Testing Graph Database Systems via Graph-Aware Metamorphic Relations
Zeyang Zhuang, Penghui Li, Pingchuan Ma, Wei Meng, and Shuai Wang
International Conference on Very Large Data Bases (VLDB ’24)Code
Evaluating C/C++ Vulnerability Detectability of Query-Based Static Application Security Testing Tools
Zongjie Li, Zhibo Liu, Wai Kin Wong, Pingchuan Ma, and Shuai Wang
IEEE Transactions on Dependable and Secure Computing (TDSC)
On Extracting Specialized Code Abilities from Large Language Models: A Feasibility Study
Zongjie Li, Chaozheng Wang, Pingchuan Ma, Chaowei Liu, Shuai Wang, Daoyuan Wu, Cuiyun Gao, and Yang Liu
International Conference on Software Engineering (ICSE ’24)arXivPress (in Chinese)
Enabling Runtime Verification of Causal Discovery Algorithms with Automated Conditional Independence Reasoning
Pingchuan Ma, Zhenlan Ji, Peisen Yao, Shuai Wang, and Kui Ren
International Conference on Software Engineering (ICSE ’24)arXivCode
InsightPilot: An LLM-Empowered Automated Data Exploration System
Pingchuan Ma, Rui Ding, Shuai Wang, Shi Han, and Dongmei Zhang
The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP ’23 Demo Track)arXiv
Explain Any Concept: Segment Anything Meets Concept-Based Explanation
Ao Sun, Pingchuan Ma, Yuanyuan Yuan, and Shuai Wang
Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS ’23)arXivPress (in Chinese)Code
Causality-Aided Trade-off Analysis for Machine Learning Fairness
Zhenlan Ji, Pingchuan Ma†, Shuai Wang†, and Yanhui Li
IEEE/ACM International Conference on Automated Software Engineering (ASE ’23)arXivCode
PerfCE: Performance Debugging on Databases with Chaos Engineering-Enhanced Causality Analysis
Zhenlan Ji, Pingchuan Ma†, and Shuai Wang
IEEE/ACM International Conference on Automated Software Engineering (ASE ’23)arXivCode
Towards Practical Federated Causal Structure Learning
Zhaoyu Wang, Pingchuan Ma†, and Shuai Wang
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD ’23)arXivCode
XInsight: eXplainable Data Analysis Through The Lens of Causality
Pingchuan Ma, Rui Ding, Shuai Wang, Shi Han, and Dongmei Zhang
ACM SIGMOD International Conference on Management of Data (SIGMOD ’23)arXivPress (in Chinese)Code
CC: Causality-Aware Coverage Criterion for Deep Neural Networks
Zhenlan Ji, Pingchuan Ma†, Yuanyuan Yuan†, and Shuai Wang
International Conference on Software Engineering (ICSE ’23)Code
sem2vec: Semantics-Aware Assembly Tracelet Embedding
Huaijin Wang, Pingchuan Ma, Shuai Wang, Qiyi Tang, Sen Nie, and Shi Wu
ACM Transactions on Software Engineering and Methodology (TOSEM)Code
Deceiving Deep Neural Networks-Based Binary Code Matching with Adversarial Programs
Wai Kin Wong, Huaijin Wang, Pingchuan Ma, Shuai Wang, Mingyue Jiang, Tsong Yueh Chen, Qiyi Tang, Sen Nie, and Shi Wu
IEEE International Conference on Software Maintenance and Evolution (ICSME ’22)Code
NoLeaks: Differentially Private Causal Discovery Under Functional Causal Model
Pingchuan Ma, Zhenlan Ji, Qi Pang, and Shuai Wang
IEEE Transactions on Information Forensics & Security (TIFS)Code
ML4S: Learning Causal Skeleton from Vicinal Graphs
Pingchuan Ma, Rui Ding, Haoyue Dai, Yuanyuan Jiang, Shuai Wang, Shi Han, and Dongmei Zhang
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD ’22)Code
Unlearnable Examples: Protecting Open-Source Software from Unauthorized Neural Code Learning
Zhenlan Ji, Pingchuan Ma, and Shuai Wang
International Conference on Software Engineering and Knowledge Engineering (SEKE ’22)Code
NeuralD: Detecting Indistinguishability Violations of Oblivious RAM with Neural Distinguishers
Pingchuan Ma, Zhibo Liu, Yuanyuan Yuan, and Shuai Wang
IEEE Transactions on Information Forensics & Security (TIFS)Code
Enhancing DNN-Based Binary Code Function Search With Low-Cost Equivalence Checking
Huaijin Wang, Pingchuan Ma, Yuanyuan Yuan, Zhibo Liu, Shuai Wang, Qiyi Tang, Sen Nie, and Shi Wu
IEEE Transactions on Software Engineering (TSE)Code
Unleashing the Power of Compiler Intermediate Representation to Enhance Neural Program Embeddings
Zongjie Li, Pingchuan Ma, Huaijin Wang, Shuai Wang, Qiyi Tang, Sen Nie, and Shi Wu
International Conference on Software Engineering (ICSE ’22)
MT-Teql: Evaluating and Augmenting Neural NLIDB on Real-world Linguistic and Schema Variations
Pingchuan Ma and Shuai Wang
International Conference on Very Large Data Bases (VLDB ’22)Code
MetaInsight: Automatic Discovery of Structured Knowledge for Exploratory Data Analysis
Pingchuan Ma, Rui Ding, Shi Han, and Dongmei Zhang
ACM SIGMOD International Conference on Management of Data (SIGMOD ’21)LinkExtended VersionReference Implementation
Metamorphic Testing and Certified Mitigation of Fairness Violations in NLP Models
Pingchuan Ma, Shuai Wang, and Jin Liu
International Joint Conference on Artificial Intelligence (IJCAI ’20)Code

Award and Grant

  • Cybersecurity Project of the Year, Tech Fest Hong Kong Awards 2025
  • SENG PhD Research Excellence Award, HKUST, 2025
  • Hong Kong ITF TSSSU Grant (0.5M HKD), Hong Kong Innovation and Technology Commission, 2025
  • Hong Kong SciTech Pioneer Award Finalist (Future Innovation Scientist), 2024
  • Researcher Access Program, OpenAI, 2024
  • Overseas Research Award, HKUST Fok Ying Tung Graduate School, 2024
  • UGC Research Travel Grant, 2023-24 Academic Year.
  • Future of Life Institute Travel Support, 2024.
  • UGC Research Travel Grant, 2022-23 Academic Year.
  • SIGMOD Student Travel Award, April 2023.
  • AISTATS "Top Reviewer", February 2023.
  • Microsoft Research Asia "Star of Tomorrow" Award, December 2022.
  • Microsoft Research Asia "Star of Tomorrow" Award, March 2022.
  • NVIDIA Academic Hardware Grant, March 2022.

Experience

  • Visiting Scholar, Sky Lab, UC Berkeley, hosted by Prof. Alvin Cheung, 2024,4 - present
  • Research Intern, Microsoft Research Asia, mentored by Justin Ding, 2022.6 - 2022.11
  • Research Intern, Microsoft Research Asia, mentored by Justin Ding, 2021.6 - 2022.4
  • Research Intern, Microsoft Research Asia, mentored by Justin Ding, 2019.12 - 2020.6

Patents

  • Pingchuan Ma, Shuai Wang, Zhaoyu Wang. Method and System for Identifying Integrity Constraints from Noisy Data. US Provisional Patent. Filing Date: 9 Jun 2024
  • Pingchuan Ma, Zhaoyu Wang, Shuai Wang. Enhanced Distributed Zero-Knowledge Proof Generation. US Patent. Filing Date: 8 April 2024
  • Shuai Wang and Pingchuan Ma. 基于大语言模型的信息处理方法和装置. Chinese Patent. Filing Date: 6 March 2025
  • Pingchuan Ma, Zhaoyu Wang, Shuai Wang. New Approach for Distributed Zero-Knowledge Proof Generation for Data Analytics Workflow. US Provisional Patent. Filing Date: 1 Nov 2024
  • Pingchuan Ma, Zhaoyu Wang, Shuai Wang. Approach for Efficient Zero-Knowledge Causal Analysis. US Provisional Patent. Filing Date: 1 Nov 2024
  • Shuai Wang and Pingchuan Ma. New Approach to Detect and Fix Unethical Outputs of Large Language Models. US Provisional Patent. Filing Date: 28 April 2024

Talk

  • Algorithm, Application and Privacy Enhancement of Causal Structure Learning, Institute of Computing Technology of the Chinese Academy of Sciences, Dec, 2024.
  • Privacy-enhancing Technologies for Causal Reasoning, HKUST (Guangzhou Campus), June, 2024.
  • Elevating Exploratory Data Analysis in The Era of Large Language Model, Huawei, 15 Dec, 2023.
  • Learning Causal Skeleton from Vicinal Graphs, Microsoft Research Asia, 5 Aug, 2022.
  • Towards Dependable and Transparent Data Analytics Platforms, Microsoft Research Asia, 10 Mar, 2022.
  • Automated Fairness Testing and Beyond, Microsoft Research Asia Causality Reading Group, 6 Sept, 2021.
  • Metamorphic Testing and Certified Mitigation of Fairness Violations in NLP Models (in Chinese), AI Time, 15 Jan, 2021.

Academic Service

  • Conference Program Committee Member/Reviewer

    • 2025: NeurIPS, ICML, LLM4Code, CHI, ICLR, AISTATS, ECML/PKDD, ACL Rolling Review
    • 2024: NeurIPS, KDD, ECML/PKDD, ACL Rolling Review, SDM, NeurIPS Ethics Review, ACML
    • 2023: KDD, AISTATS, NeurIPS Ethics Review, ECML/PKDD, FAccT, SIGMOD ARI, Queer in AI @ ACL, PETS Artifact Evaluation
    • 2022: PETS Artifact Evaluation, ISSTA Artifact Evaluation, EuroSys Artifact Evaluation

  • Journal Reviewer

    • Empirical Software Engineering, Harvard Data Science Review, Scientific Reports, Journal of Systems & Software (JSS), International Journal of Computer Vision (IJCV), IEEE Signal Processing Letters (SPL), Computational Statistics and Data Analysis

Teaching Experience

  • Teaching Assistant, COMP4901N: Competitive Programming in Cybersecurity (Fall 2021)
  • Teaching Assistant, COMP6613C: Topics in Computer Security and Privacy (Spring 2021)