Xiyue Zhang

Xiyue Zhang

University of Bristol

About

Xiyue Zhang (Pronounced: Shee-you-eh Jahng) is a Lecturer (US equiv. Assistant Professor) in the School of Computer Science at the University of Bristol. Her current research mainly focuses on trustworthy deep learning, formal modelling and verification. Previously, she was a postdoctoral research associate working with Prof. Marta Kwiatkowska in the Department of Computer Science at the University of Oxford. She received her Ph.D. in Applied Mathematics, advised by Prof. Meng Sun, and her B.Sc. in Information and Computing Science from School of Mathematical Sciences, Peking University.

Recruitment

I am looking for motivated PhD students to join my group and work on: (i) formal verification of AI-enabled systems; (ii) empirical analysis and testing of data-driven models and systems; and (iii) agentic AI for software engineering. Applicants should have a strong background in computer science or a closely related field and an interest in developing rigorous methods for understanding and assuring complex AI systems. A range of funding opportunities may be available to both UK and international applicants, including University and UKRI funded scholarships, CDT studentships, joint UoB-CSC scholarships, and other funding schemes.

How to Apply

If you are interested in joining my group, please email me with: (i) Your CV; (ii) Academic transcripts; (iii) A brief description of your research interests, relevant experience, and the topics you would be interested in exploring. Please also indicate the degree or position you are applying for and any funding scheme you intend to pursue.

🔥 News

  • 2026.07:  🎉🎉 Our paper, Calibrated Adversarial Sampling: Stabilizing Multi-Attack Adversarial Training via Bandit Optimization, has been accepted by ACM MM 2026.
  • 2026.06:  🎉🎉 Our paper, Privacy-Preserving Robustness Verification for Neural Networks, has been accepted by UAI 2026.
  • 2025.10:  🎉🎉 Our paper, Risk-Averse Certification of Bayesian Neural Networks, has been accepted by SETTA 2025.
  • 2025.07:  🎉🎉 Our paper, PREMAP: A Unifying PREiMage APproximation Framework for Neural Networks, has been accepted by Journal of Machine Learning Research (JMLR).
  • 2025.06:  🎉🎉 Our paper “Protecting Deep Learning Model Copyrights with Adversarial Example-Free Reuse Detection” has been accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS). Check out the arxiv version here.
  • 2025.03:  🎉🎉 Great honour to win the Research Commercialisation Award. Huge thanks to those who support me at the competition night! Check out more info here.
  • 2025.03:  🎉🎉 Our paper “Runtime Backdoor Detection for Federated Learning via Representational Dissimilarity Analysis” has been accepted by IEEE Transactions on Dependable and Secure Computing (TDSC). Check out the arxiv version here.
  • 2025.01:  🎟️🎟️ I am happy to serve on the panel for the AI4CI (Artificial Intelligence for Collective Intelligence) hub ECR event. Look forward to an engaging discussion!
  • 2024.11:  🎉🎉 I am honoured to present an inaugural talk on Neural Network Certification to kick off the Trustworthy Systems Lab (TSL) seminar series at the University of Bristol. Join our Teams channel for more details. This is an open group, so feel free to spread the word! To observe, participate in debates, or present, please reach out. Join our mailing list for weekly invitations and updates on future talks.
  • 2024.08:  🎉🎉 Our paper “FAST: Boosting Uncertainty-based Test Prioritization Methods for Neural Networks via Feature Selection” is accpeted by ASE 2024.
  • 2024.07:   ✈️✈️ I give a talk at SAIV 2024 speaking on preimage approximation-based neural network analysis.
  • 2024.05:  🎉🎉 Our paper “Automated Design of Linear Bounding Functions for Sigmoidal Nonlinearities in Neural Networks” is accpeted by ECML PKDD 2024.

📝 Selected Publications

A complete list of my publications can be found in Google Scholar.

Preprint

  • From Verdict to Diagnosis: Attributable Security Review of Pull Requests
    Zhuo Chen, Boyang Wang, Xiyue Zhang, Xiaoyun Xu, Ahmad-Reza Sadeghi, Stjepan Picek, Lichao Wu
    [arxiv]

Conference

  • Stabilizing Multi-Attack Adversarial Training via Bandit Optimization (ACM MM 2026)
    Rui Wang, Zeming Wei, Xiyue Zhang, Meng Sun
    [arxiv]

  • Privacy-Preserving Robustness Verification for Neural Networks (UAI 2026)
    Nianyun Song, Xiaokun Luan, Yu Guo, Rongfang Bie, Meng Sun, Xiyue Zhang
    [link] [arxiv]

  • FAST: Boosting Uncertainty-based Test Prioritization Methods for Neural Networks via Feature Selection (ASE 2024)
    Jialuo Chen, Jingyi Wang, Xiyue Zhang, Youcheng Sun, Marta Kwiatkowska, Jiming Chen, Peng Cheng
    [link] [arxiv] [code]

  • Automated Design of Linear Bounding Functions for Sigmoidal Nonlinearities in Neural Networks (ECML-PKDD 2024)
    Matthias König, Xiyue Zhang, Holger H Hoos, Marta Kwiatkowska, Jan N van Rijn
    [link] [arxiv] [code]

  • Provable Preimage Under-Approximation for Neural Networks (TACAS 2024)
    Xiyue Zhang, Benjie Wang, Marta Kwiatkowska
    [link] [arxiv] [code]

  • Decision-Guided Weighted Automata Extraction from Recurrent Neural Networks (AAAI 2021)
    Xiyue Zhang, Xiaoning Du, Xiaofei Xie, Lei Ma, Yang Liu, Meng Sun
    [link]

  • Towards Characterizing Adversarial Defects of Deep Learning Software from the Lens of Uncertainty (ICSE 2020)
    Xiyue Zhang, Xiaofei Xie, Lei Ma, Xiaoning Du, Qiang Hu, Yang Liu, Jianjun Zhao, Meng Sun
    [link] [arxiv]

Journal

  • PREMAP: A Unifying PREiMage APproximation Framework for Neural Networks (Journal of Machine Learning Research)
    Xiyue Zhang, Benjie Wang, Marta Kwiatkowska, Huan Zhang
    [link] [arxiv]

  • Runtime Backdoor Detection for Federated Learning via Representational Dissimilarity Analysis (IEEE Transactions on Dependable and Secure Computing)
    Xiyue Zhang, Xiaoyong Xue, Xiaoning Du, Xiaofei Xie, Yang Liu, Meng Sun
    [link]

  • Protecting Deep Learning Model Copyrights with Adversarial Example-Free Reuse Detection (IEEE Transactions on Neural Networks and Learning Systems)
    Xiaokun Luan, Xiyue Zhang, Jingyi Wang, Meng Sun
    [link] [arxiv]

  • Weighted Automata Extraction and Explanation of Recurrent Neural Networks for Natural Language Tasks (Journal of Logical and Algebraic Methods in Programming)
    Zeming Wei, Xiyue Zhang, Yihao Zhang, Meng Sun
    [link] [arxiv] [code]

  • DeepGlobal: A Framework for Global Robustness Verification of Feedforward Neural Networks (Journal of Systems Architecture)
    Weidi Sun, Yuteng Lu, Xiyue Zhang, Meng Sun
    [link]

  • A Formal Framework Capturing Real-Time and Stochastic Behavior in Connectors (Science of Computer Programming)
    Yi Li, Xiyue Zhang, Yuanyi Ji, Meng Sun
    [link]

  • Reasoning about Connectors Using Coq and Z3 (Science of Computer Programming)
    Xiyue Zhang, Weijiang Hong, Yi Li, Meng Sun
    [link]

🏫 Teaching

Xiyue Zhang teaches across a range of undergraduate Computer Science programmes, including first-year mathematical foundations to advanced topics in machine learning and artificial intelligence. Her teaching currently includes Mathematics for Computer Science, Machine Learning, and Artificial Intelligence Algorithms and Tools, covering both theoretical principles and practical techniques that underpin modern AI systems.

Teaching Units

2026-27

  • TB1 Mathematics for Computer Science A (Year-1 UG)
  • TB2 AI Tools and Methods (Year-2 UG)

2025-26

  • TB1 Mathematics for Computer Science A (Year-1 UG)
  • TB1 Machine Learning (Year-3 UG)

💼 Service

Recent School Service

Selected Recent Academic Service

  • 41st Annual AAAI Conference on Artificial Intelligence (AAAI 2027). Programme Committee Member.
  • 34th ACM International Conference on Multimedia (ACM MM 2026). Programme Committee Member.
  • International Joint Conferences on Artificial Intelligence 2026 (IJCAI 2026). Programme Committee Member.
  • European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2026). Programme Committee Member.
  • 27th International Conference on Formal Engineering Methods (ICFEM 2026). Programme Committee Member.
  • 12th International Symposium on Dependable Software Engineering Theories, Tools and Applications (SETTA 2026). Programme Committee Member.
  • 33rd Asia-Pacific Software Engineering Conference (APSEC 2026). Programme Committee Member.

🎖 Honors and Awards

  • 2025.03 Research Commercialisation Award
  • 2023.10 DAAD AInet fellow for the Postdoc-NeT-AI
  • 2023.08 Future Digileaders Award 2023 (by Digital Futures for early-career researchers)
  • 2022.06 Doctoral Dissertation Award of Peking University
  • 2020&2021.10 National Scholarship (Highest-level scholarship 0.1%)

📖 Education

  • 2017.09 - 2022.06, PhD in Applied Mathematics, School of Mathematical Sciences, Peking University.
  • 2019.02 - 2020.03, Research Assistant, School of Computer Science & Engineering, Nanyang Technological University.
  • 2017.08: Visiting Student, Singapore University of Technology and Design.
  • 2013.09 - 2017.06, BSc in Information and Computing Science, School of Mathematical Sciences, Peking University.