Zhaoyu Wang

As of 9 November 2026
A photo of Zhaoyu Wang

Welcome to my homepage!

I am a Ph.D. student in the Department of Computer Science and Engineering at The Hong Kong University of Science and Technology (HKUST), under the supervision of Prof. Shuai Wang. Prior to joining HKUST, I obtained my bachelor’s degree in data science and technology from Tongji University, Shanghai, China in 2023. My research focuses on end-to-end privacy-preserving and verifiable data management, with an emphasis on zero-knowledge proof (ZKP) systems for analytical workflows.

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

Curriculum Vitae (PDF)

Publication

(* Equal contribution)

Sound Debloating of Redundant Checks in Zero-Knowledge Machine-Learning Circuits
Zhantong Xue, Pingchuan Ma, Zhaoyu Wang, Yuguang Zhou, Huaijin Wang, and Shuai Wang
ACM Conference on Computer and Communications Security (CCS 2026). Forthcoming.
Privacy-preserving and Verifiable Causal Prescriptive Analytics
Zhaoyu Wang, Pingchuan Ma, Zhantong Xue, Yanbo Dai, Zhenlan Ji, and Shuai Wang
ACM SIGMOD International Conference on Management of Data (SIGMOD 2026)
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 2026)
Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric Approach
Zhenlan Ji, Pingchuan Ma, Zongjie Li, Zhaoyu Wang, and Shuai Wang
ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2025)
Reeq: Testing and Mitigating Ethically Inconsistent Suggestions of Large Language Models with Reflective Equilibrium
Pingchuan Ma*, Zhaoyu Wang*, Zongjie Li, Zhenlan Ji, Ao Sun, Juergen Rahmel, and Shuai Wang
ACM Transactions on Software Engineering and Methodology (TOSEM 2025)
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 2024)code
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 2023)arXivcode

Preprints

(† Corresponding author)

AutoSpec: Safety Rule Evolution for LLM Agents via Inductive Logic Programming
Pingchuan Ma, Zhaoyu Wang†, Zimo Ji, Yuguang Zhou, Zhantong Xue, Zongjie Li, Shuai Wang, and Xiaoqin Zhang
arXiv preprintarXiv
From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails
Yuguang Zhou, Xunguang Wang, Pingchuan Ma, Zhantong Xue, Zhaoyu Wang, and Shuai Wang
arXiv preprintarXiv
ZK-Value: A Practical Zero-Knowledge System for Verifiable Data Valuation
Zhaoyu Wang, Pingchuan Ma, Zhantong Xue, Yuguang Zhou, Qixin Zhang, Xiaoqin Zhang, and Shuai Wang
arXiv preprintarXiv
From Evaluation to Enhancement: Large Language Models for Zero-Knowledge Proof Code Generation
Zhantong Xue, Pingchuan Ma, Zhaoyu Wang, Yuguang Zhou, Xiaoqin Zhang, Shuai Wang, and Juergen Rahmel
arXiv preprintarXiv
A zk-SNARK Programming Framework for Verifiable Data Analytics
Zhantong Xue, Pingchuan Ma, Zhaoyu Wang, Yuguang Zhou, and Shuai Wang
IACR Cryptology ePrint ArchiveePrint

Education

  • Ph.D. in Computer Science and Engineering, The Hong Kong University of Science and Technology, Sep. 2023 - Now
  • Exchange, École Polytechnique Fédérale de Lausanne, Sep. 2022 - Jan. 2023
  • B.Eng. in Data Science and Technology, Tongji University, Sep. 2019 - Jun. 2023

Award and Grant

  • SIGMOD Student Travel Grant, June 2026
  • FinTech Award (Bronze), Hong Kong ICT Awards 2025
  • Cybersecurity Project of the Year, Tech Fest Hong Kong Awards 2025
  • UGC Research Travel Grant, 2025-26 Academic Year.
  • UGC Research Travel Grant, 2024-25 Academic Year.
  • UGC Research Travel Grant, 2023-24 Academic Year.

Patents and Technology Transfer

  • Pingchuan Ma, Zhaoyu Wang, Shuai Wang, and Xiaoqin Zhang. Method for Verifying String Profiling Results Based on Zero-Knowledge Proofs. CN 202611024917.4. Filing Date: 10 Jul 2026
  • Pingchuan Ma, Shuai Wang, Zhaoyu Wang. Method and System for Identifying Integrity Constraints from Noisy Data. CN 202610706202.0. Filing Date: 21 May 2026
  • Pingchuan Ma, Shuai Wang, Zhaoyu Wang. Enhanced Zero-Knowledge Analysis. US 19/257400, CN 202510956434.7, HK 42026123482.7. Filing Date: 1 Jul 2025. Licensed to industry.
  • Pingchuan Ma, Shuai Wang, Zhaoyu Wang. Enhanced Distributed Zero-Knowledge Proof Generation. US 19/173756, CN 202510892963.5, HK 42026123481.9. Filing Date: 8 Apr 2025. Licensed to industry.

Enhanced Zero-Knowledge Analysis and Enhanced Distributed Zero-Knowledge Proof Generation were licensed by HKUST R&D Corporation to CipherInsight Limited, a Hong Kong fintech startup, in March 2025.

Professional Service

  • Sub-Reviewer of S&P'27, ICML'26, OOPSLA'26, ASE'25, CCS'25, ICML'25, NeurIPS'25, S&P'25, ACL Rolling Review'25, LLM4Code'25, FSE'24, ECML-PKDD'23, PETS'23, and IEEE TC (2026).

Teaching Experience

  • Teaching Assistant, COMP 4331: Data Mining (Fall 2025)
  • Teaching Assistant, COMP 2011: Programming with C++ (Fall 2024)