Dr. Dawei Zhou
Assistant Professor Master Supervisor
Email: dwzhou@cityu.edu.mo
Tel: (853)85902425
Office address: Room S401, Stanley Ho Building, City University of Macau (Taipa)
Educational experience
2024 PhD. in Information and Telecommunication Engineering, Xidian University, China
2019 B.Sc. in Telecommunications Engineering, Xidian University, China
Incumbent
Assistant Professor, Faculty of Data Science, City University of Macau
Research interests
Trustworthy Machine Learning: Adversarial Robustness, Privacy Protection, Forgery detection
AI for Healthcare：Medical imaging enhancement、Reliable automatic diagnosis
Visual Content Generation：Heterogeneous Image Synthesis, Multi-modal generation
Research and publications
Refereed Journal Articles
Zhou, D., Wang, N., Liu, T., & Gao, X. (2025). Improving Adversarial Training From the Perspective of Class-Flipping Distribution. IEEE Transactions on Pattern Analysis and Machine Intelligence. (IF=18.6)
Zhou, D., Wang, N., Han, B., Liu, T., & Gao, X. (2025). Defending Against Adversarial Examples Via Modeling Adversarial Noise. International Journal of Computer Vision, 1-18. (IF=9.3)
Zhou, D., Su, Z., Liu, D., Liu, T., Wang, N., & Gao, X. (2025). A Knowledge-guided Adversarial Defense for Resisting Malicious Visual Manipulation. IEEE Transactions on Dependable and Secure Computing. (IF=7.5)
Zhou, D., Qu, H., Wang, N., Peng, C., Ma, Z., Yang, X., & Gao, X. (2025). Fooling human detectors via robust and visually natural adversarial patches. Neurocomputing, 616, 128915. (IF=6.5)
Zhou, D., Wang, N., Peng, C., Yu, Y., Yang, X., & Gao, X. (2021). Towards multi-domain face synthesis via domain-invariant representations and multi-level feature parts. IEEE Transactions on Multimedia, 24, 3469-3479. (IF=9.7)
Xia, R., Zhou, D., Liu, D., Li, J., Yuan, L., Wang, N., & Gao, X. (2024). Inspector for face forgery detection: Defending against adversarial attacks from coarse to fine. IEEE Transactions on Image Processing. (IF=13.7)
Hu, L., Zhou, D., Xu, J., Lu, C., Han, C., Shi, Z., ... & Liu, Z. (2024). Protecting prostate cancer classification from rectal artifacts via targeted adversarial training. IEEE Journal of Biomedical and Health Informatics, 28(7), 3997-4009. (IF=6.8)
Hu, L., Zhou, D. W., Zha, Y. F., Li, L., He, H., Xu, W. H., ... & Zhao, J. G. (2021). Synthesizing High-b-Value Diffusion–weighted Imaging of the Prostate Using Generative Adversarial Networks. Radiology: Artificial Intelligence, 3(5), e200237. (IF=13.2)
Hu, L., Zhou, D. W., Fu, C. X., Benkert, T., Jiang, C. Y., Li, R. T., ... & Zhao, J. G. (2021). Advanced zoomed diffusion-weighted imaging vs. full-field-of-view diffusion-weighted imaging in prostate cancer detection: a radiomic features study. European radiology, 31(3), 1760-1769. (IF=4.7)
Li, Q., Wu, D., Zhou, D., Lin, C., Liu, S., Wang, C., & Shen, C. (2025). Robust Adversarial Defenses in Federated Learning: Exploring the Impact of Data Heterogeneity. IEEE Transactions on Information Forensics and Security. (IF=8.0)
Liu, L., Wang, N., Zhou, D., Liu, D., Yang, X., Gao, X., & Liu, T. (2024). Generalizable Prompt Learning via Gradient Constrained Sharpness-Aware Minimization. IEEE Transactions on Multimedia. (IF=9.7)
Hu, L., Guo, X., Zhou, D., Wang, Z., Dai, L., Li, L., ... & Liu, Z. (2024). Development and validation of a deep learning model to reduce the interference of rectal artifacts in MRI-based prostate cancer diagnosis. Radiology: Artificial Intelligence, 6(2), e230362. (IF=13.2)
Yang, Y., Lin, C., Li, Q., Zhao, Z., Fan, H., Zhou, D., ... & Shen, C. (2024). Quantization aware attack: Enhancing transferable adversarial attacks by model quantization. IEEE Transactions on Information Forensics and Security, 19, 3265-3278. (IF=8.0)
Refereed Conference Articles
Zhou, D., Wang, N., Yang, H., Gao, X., & Liu, T. (2023, July). Phase-aware adversarial defense for improving adversarial robustness. In International Conference on Machine Learning (pp. 42724-42741). PMLR. (CCF-A)
Zhou, D., Chen, Y., Wang, N., Liu, D., Gao, X., & Liu, T. (2023, July). Eliminating adversarial noise via information discard and robust representation restoration. In International Conference on Machine Learning (pp. 42517-42530). PMLR. (CCF-A)
Zhou, D., Wang, N., Han, B., & Liu, T. (2022, June). Modeling adversarial noise for adversarial training. In International Conference on Machine Learning (pp. 27353-27366). PMLR. (CCF-A)
Zhou, D., Wang, N., Gao, X., Han, B., Wang, X., Zhan, Y., & Liu, T. (2022, June). Improving adversarial robustness via mutual information estimation. In International Conference on Machine Learning (pp. 27338-27352). PMLR. (CCF-A)
Zhou, D., Liu, T., Han, B., Wang, N., Peng, C., & Gao, X. (2021, July). Towards defending against adversarial examples via attack-invariant features. In International conference on machine learning (pp. 12835-12845). PMLR. (CCF-A)
Zhou, D., Wang, N., Peng, C., Gao, X., Wang, X., Yu, J., & Liu, T. (2021). Removing adversarial noise in class activation feature space. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 7878-7887). (CCF-A)
Xu, Y., Zhou, D., Liu, D., & Wang, N. Phase and Amplitude-aware Prompting for Enhancing Adversarial Robustness. In Forty-second International Conference on Machine Learning. (CCF-A)
Xu, J., Zhou, D., Hu, L., Guo, J., Yang, F., Liu, Z., ... & Gao, X. (2025, April). Motion Artifact Removal in Pixel-Frequency Domain via Alternate Masks and Diffusion Model. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 8, pp. 8878-8886). (CCF-A)
Zhou, N., Zhou, D., Liu, D., Wang, N., & Gao, X. (2025, April). Mitigating feature gap for adversarial robustness by feature disentanglement. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 10, pp. 10825-10833). (CCF-A)
Xia, R., Zhou, D., Liu, D., Yuan, L., Wang, S., Li, J., ... & Gao, X. (2024, October). Advancing generalized deepfake detector with forgery perception guidance. In Proceedings of the 32nd ACM International Conference on Multimedia (pp. 6676-6685). (CCF-A)
Su, Z., Zhou, D., Wang, N., Liu, D., Wang, Z., & Gao, X. (2023). Hiding visual information via obfuscating adversarial perturbations. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 4356-4366). (CCF-A)
Zhang, J., Liu, F., Zhou, D., Zhang, J., & Liu, T. (2024, July). Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training. In International Conference on Machine Learning (pp. 59382-59402). PMLR. (CCF-A)
Academic Award
2023 UAI 2023 Top Reviewer
