Research

It has been a long journey.

Research Interests

• Trustworthy agentic AI, Adversarial Robustness, Safety Verification

Publications

• Y. Jiang, J. Zhao, Y. Yuan, T. Zhang, Y. Huang, Y. Zhang, Y. Wang, Y. Li, X. Guo, Y. Zhao, H. Zhou, J. Zhang, Z. Zhang, X. Lin, Y. Zou, H. Ma, Y. Shang, Y. Hu, K. Cai, R. Zhang, B. Chen, Y. Gao, Z. Jiao, Y. Qin, S. Du, X. Tong, Z. Liu, Y. Chen, X. Rong, R. Wang, Y. Zheng, Z. Fan, M. Sensoy, H. Zhang, P. Zhou, L. Jin, H. Zhao, X. Yang, J. Zhao, J. Li, J. Zhou, Z. Cheng, L. Huang, Z. Liu, Z. Zhu, J. Li, G. Wang, Q. Li, X. Zhang, Y. Yang, M. Ye, W. Ren, Z. He, H. Su, R. Ni, L. Jing, X. Wei, J. Xing, M. Alioto, S. Shen, P. Radeva, D. Tao, Y. Zhang, S. Yan and X. Li. Never Compromise with Vulnerabilities: A Comprehensive Survey on AI Governance, Science China Information Sciences (2026).
• Y. Dong, R. Mu, Y. Zhang, S. Sun, T. Zhang, C. Wu, G. Jin, Y. Qi, J. Hu, J. Meng, S. Bensalem and X. Huang. Safeguarding Large Language Models: A Survey, Artificial Intelligence Review (2025).
• X. Huang, W. Ruan, W. Huang, G. Jin, Y. Dong, C. Wu, S. Bensalem, R. Mu, Y. Qi, X. Zhao, K. Cai, Y. Zhang, S. Wu, P. Xu, D. Wu, A. Freitas and M. A. Mustafa. A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation, Artificial Intelligence Review (2024).
• Y. Zhang, W. Ruan, F. Wang and X. Huang. Generalizing universal adversarial perturbations for deep neural networks, Machine Learning, 112(5): 1597-1626 (2023).
• S. Zeng, B. Zhang, Y. Zhang and J. Gou. Dual Sparse Learning via Data Augmentation for Robust Facial Image Classification, International Journal of Machine Learning and Cybernetics, 11(3): 1717–1734 (2020).
• Y. Zhang, S. Zeng, W. Zeng and J. Gou. GNN-CRC: Discriminative Collaborative Representation-Based Classification via Gabor Wavelet Transformation and Nearest Neighbor, J. Shanghai Jiao Tong Univ. (Sci.), 23(5): 657-665 (2018).

Conferences

• B. Brückner, A. J. Mercado, Y. Zhang, P. Kouvaros and A. Lomuscio. IoUCert: Robustness Verification for Anchor-based Object Detectors, European Conference on Computer Vision (ECCV 2026).
• Y. Zhang, P. Kouvaros and A. Lomuscio. Scalable Neural Network Geometric Robustness Validation via Hölder Optimisation, The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025).
• F. Wang, Y. Zhang, X. Yin, G. Cheng, Z. Fu, X. Huang and W. Ruan. A Black-Box Evaluation Framework for Semantic Robustness in Bird's Eye View Detection, Association for the Advancement of Artificial Intelligence (AAAI 2025).
• T. Zhang, Y. Zhang, R. Mu, J. Liu, J. Fieldsend and W. Ruan. PRASS: Probabilistic Risk-averse Robust Learning with Stochastic Search, International Joint Conference on Artificial Intelligence (IJCAI 2024).
• Y. Zhang, T. Zhang, R. Mu, X. Huang and W. Ruan. Towards Fairness-Aware Adversarial Learning, Conference on Computer Vision and Pattern Recognition (CVPR 2024). [Code]
• R. Mu, L. Marcolino, Y. Zhang, T. Zhang, X. Huang and W. Ruan. Reward Certification for Policy Smoothed Reinforcement Learning, Association for the Advancement of Artificial Intelligence (AAAI 2024). [Code]
• T. Zhang, J. Liu, Y. Zhang, R. Mu, X. Huang and W. Ruan. DeepGRE: Global Robustness Evaluaion of Deep Neural Networks, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024).
• F. Wang, Z. Fu, Y. Zhang and W. Ruan. Self-adaptive Adversarial Training for Robust Medical Segmentation, Medical Image Computing and Computer Assisted Intervention (MICCAI 2023). [Code]
• F. Wang, Y. Zhang, Y. Zheng and W. Ruan. Dynamic Efficient Adversarial Training Guided by Gradient Magnitude, NeurIPS 2022 TEA Workshop. [Code]
• Y. Zhang, F. Wang and W. Ruan. Fooling Object Detectors: Adversarial Attacks by Half-Neighbor Masks, CIKM 2020 AnalytiCup Workshop. [Code]
• Y. Zhang, W. Ruan, F. Wang, and X. Huang. Generalizing Universal Adversarial Attacks Beyond Additive Perturbations, The IEEE International Conference on Data Mining (ICDM 2020), November 17-20, 2020, Sorrento, Italy. [Code] [Video]
• S. Zeng, B. Zhang, Y. Zhang and J. Gou. Collaboratively Weighting Deep and Classic Representation via L2 Regularization for Image Classification, Proceedings of The 10th Asian Conference on Machine Learning, PMLR 95:502-517, 2018.
• Y. Zhang, S. Zeng, W. Zeng and H. Jiang. Synthetic Training Samples for Enhanced Locality-Constrained Dictionary Learning, The 2nd Asian Conference on Artificial Intelligence Technology (2018), Chongqing, China, Jun. 8-10. The Journal of Engineering, (2018) 2018(16): 1761-1767. [Oral Presentation, Best Session Paper]

Work Experience

• • Senior Reseach Scientist: Safe Intelligence, Working on Verification, June 2025 - Present.
• • Reseach Associate: Imperial College London, in Safe Artificial Intelligence Lab (SAIL). Working on project EVENFLOW, September 2024 - Present.
• • Reseach Assistant: University of Liverpool, part-time in Trustworthy ACPS Lab. Working on projects FOCETA and EnnCore, January 2023 - September 2024.

Teaching Assistant

• TA for ECMM422 Machine Learning, University of Exeter, 2021
• TA for ECMM458 Machine Learning (professional), University of Exeter, 2020
• PGR Demonstrator for MSc AI/DS Students, University of Exeter, 2020-2021

Academic Services

• Journal Reviewer: IEEE Transactions on Knowledge and Data Engineering/Information Sciences/Machine Vision and Applications/The Visual Computer/International Journal of Computer Vision
• Conference Reviewer: ICLR/NeurIPS/ECCV/CVPR/ICCV/CIKM/ICCV/ICML/AISTATS/AAAI
• External Conference Reviewer: ECML-PKDD/IJCAI/ECAI