Professional Education


  • Doctor of Philosophy, University of Oxford, Computer Science (2022)

Stanford Advisors


Current Research and Scholarly Interests


Responsible AI, AI safety, trustworthy AI, robustness, explainability and interpretability.
Formal methods, automated verification, verification of deep neural networks, formal explainable AI.

All Publications


  • Towards Efficient Verification of Quantized Neural Networks Huang, P., Wu, H., Yang, Y., Daukantas, I., Wu, M., Zhang, Y., Barrett, C., Wooldridge, M., Dy, J., Natarajan, S. ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2024: 21152-21160
  • Parallel Verification for δ-Equivalence of Neural Network Quantization Huang, P., Yang, Y., Wu, H., Daukantas, I., Wu, M., Jia, F., Barrett, C., Avni, G., Giacobbe, M., Johnson, T. T., Katz, G., Lukina, A., Narodytska, N., Schilling, C. SPRINGER INTERNATIONAL PUBLISHING AG. 2024: 78-99
  • Marabou 2.0: A Versatile Formal Analyzer of Neural Networks Wu, H., Isac, O., Zeljic, A., Tagomori, T., Daggitt, M., Kokke, W., Refaeli, I., Amir, G., Julian, K., Bassan, S., Huang, P., Lahav, O., Wu, M., Zhang, M., Komendantskaya, E., Katz, G., Barrett, C., Ganesh, Gurfinkel, A. SPRINGER INTERNATIONAL PUBLISHING AG. 2024: 249-264
  • Convex Bounds on the Softmax Function with Applications to Robustness Verification Proceedings of The 26th International Conference on Artificial Intelligence and Statistics Wei, D., Wu, H., Wu, M., Chen, P., Barrett, C., Farchi, E. 2023: 6853-6878
  • <i>Soy</i>: An Efficient MILP Solver for Piecewise-Affine Systems Wu, H., Wu, M., Sadigh, D., Barrett, C., IEEE IEEE. 2023: 6281-6288
  • Full Poincare polarimetry enabled through physical inference OPTICA He, C., Lin, J., Chang, J., Antonello, J., Dai, B., Wang, J., Cui, J., Qi, J., Wu, M., Elson, D. S., Xi, P., Forbes, A., Booth, M. J. 2022; 9 (10): 1109-1114
  • A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability? COMPUTER SCIENCE REVIEW Huang, X., Kroening, D., Ruan, W., Sharp, J., Sun, Y., Thamo, E., Wu, M., Yi, X. 2020; 37
  • A game-based approximate verification of deep neural networks with provable guarantees THEORETICAL COMPUTER SCIENCE Wu, M., Wicker, M., Ruan, W., Huang, X., Kwiatkowska, M. 2020; 807: 298-329
  • Assessing Robustness of Text Classification through Maximal Safe Radius Computation Findings of the Association for Computational Linguistics: EMNLP 2020 La Malfa, E., Wu, M., Laurenti, L., Wang, B., Hartshorn, A., Kwiatkowska, M. 2020: 2949-2968
  • Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for the Hamming Distance Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence Ruan, W., Wu, M., Sun, Y., Huang, X., Kroening, D., Kwiatkowska, M. 2019: 5944-5952

    View details for DOI 10.24963/ijcai.2019/824

  • Concolic Testing for Deep Neural Networks Sun, Y., Wu, M., Ruan, W., Huang, X., Kwiatkowska, M., Kroening, D., Huchard, M., Kastner, C., Fraser, G. IEEE. 2018: 109-119