萬偉 博士
助理教授 碩導
學校郵箱：weiwan@cityu.edu.mo
辦公電話：(853)85902424
辦公地址：澳門城市大學(氹仔)蔡繼有樓N406室
學歷
2025 網絡空間安全博士, 華中科技大學, 中國
2021 軟件工程碩士, 華中科技大學, 中國
2018 軟件工程學士, 武漢工程大學, 中國
研究方向
人工智能安全、腦機接口、具身智能、聯邦學習
研究及出版
1. Hangtao Zhang, Yucheng Zhao, Sishun Liu, Ziqi Zhou, Zeyu Ye, Wei Wan, Minghui Li, Shengshan Hu, Yanjun Zhang, Yi Liu, Leo Yu Zhang. Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics. USENIX Security Symposium (USENIX Security), 2026. (CCF A, 唯一通訊作者)
2. Wei Wan, Ning Yuxuan, Zhicong Huang, Cheng Hong, Shengshan Hu, Ziqi Zhou, Yechao Zhang, Tianqing Zhu, Wanlei Zhou, Leo Yu Zhang. MARS: A Malignity-Aware Backdoor Defense in Federated Learning. 39th Conference on Neural Information Processing Systems (NeurIPS), 2025. (CCF A)
3. Minghui Li, Hangtao Zhang, Yanjun Zhang, Li Zeng, Chao Chen, Qiyun Shao, Wei Wan, Shengshan Hu, Leo Yu Zhang. Fine-Grained Poisoning Framework Against Federated Learning. IEEE Transactions on Dependable and Secure Computing (TDSC), 2025. (CCF A)
4. Minghui Li, Yuanhang Wang, Peijin Guo, Wei Wan, Shengshan Hu, Shengqing Hu. HiF-DTA: Hierarchical Feature Learning Network for Drug-Target Affinity Prediction. 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2025. (CCF B)
5. Minghui Li, Hao Zhang, Yechao Zhang, Wei Wan, Shengshan Hu, Jing Wang. Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025. (CCF B)
6. Ziqi Zhou, Menghao Deng, Yufei Song, Hangtao Zhang, Wei Wan, Shengshan Hu, Minghui Li, Leo Yu Zhang, and Dezhong Yao. DarkHash: A Data-Free Backdoor Attack Against Deep Hashing. IEEE Transactions on Information Forensics and Security (TIFS), 2025. (CCF A, 唯一通讯作者)
7. Minghui Li, Yao Shi, Shengqing Hu, Shengshan Hu, Peijin Guo, Wei Wan, Leo Yu Zhang, Shirui Pan, Jizhou Li, Lichao Sun, and others. MVSF-AB: Accurate Antibody–Antigen Binding Affinity Prediction via Multi-View Sequence Feature Learning. Bioinformatics, 2025. (CCF B)
8. Minghui Li, Lei Yu, Hewen Pan, Shengqing Hu, Longling Zhang, Shengshan Hu, Wei Wan, and Peijin Guo. An Efficient Residual-based Low-dose PET Reconstruction with Spatial-Frequency Integration. International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025. (CCF B)
9. Peijin Guo, Minghui Li, Hewen Pan, Ruixiang Huang, Lulu Xue, Shengqing Hu, Zikang Guo, Wei Wan, and Shengshan Hu. Multi-modality Representation Learning for Antibody-Antigen Interactions Prediction. International Conference on Multimedia and Expo (ICME), 2025. (CCF B)
10. Ziqi Zhou, Bowen Li, Yufei Song, Zhifei Yu, Shengshan Hu, Wei Wan, Leo Yu Zhang, Dezhong Yao, and Hai Jin. Numbod: A Spatial-Frequency Fusion Attack Against Object Detectors. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2025. (CCF A, 共同通讯作者)
11. Yichen Wang, Yuxuan Chou, Ziqi Zhou, Hangtao Zhang, Wei Wan, Shengshan Hu, and Minghui Li. Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2025. (CCF A, 唯一通讯作者)
12. Yufei Song, Ziqi Zhou, Minghui Li, Xianlong Wang, Hangtao Zhang, Menghao Deng, Wei Wan, Shengshan Hu, and Leo Yu Zhang. PB-UAP: Hybrid Universal Adversarial Attack for Image Segmentation. International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025. (CCF B)
13. Xianlong Wang, Shengshan Hu, Yechao Zhang, Ziqi Zhou, Leo Yu Zhang, Peng Xu, Wei Wan, and Hai Jin. ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification. European Symposium on Research in Computer Security (ESORICS), 2024. (CCF B)
14. Yechao Zhang, Shengshan Hu, Leo Yu Zhang, Junyu Shi, Minghui Li, Xiaogeng Liu, Wei Wan, and Hai Jin. Why Does Little Robustness Help? A Further Step towards Understanding Adversarial Transferability. IEEE Symposium on Security and Privacy (S&P), 2024. (CCF A)
15. Minghui Li, Wei Wan, Yuxuan Ning, Shengshan Hu, Lulu Xue, Leo Yu Zhang, and Yichen Wang. DarkFed: A Data-Free Backdoor Attack in Federated Learning. International Joint Conference on Artificial Intelligence (IJCAI), 2024. (CCF A, 共同第一作者&唯一通讯作者)
16. Wei Wan, Yuxuan Ning, Shengshan Hu, Lulu Xue, Minghui Li, Leo Yu Zhang, and Hai Jin. MISA: Unveiling the Vulnerabilities in Split Federated Learning. International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024. (CCF B)
17. Ziqi Zhou, Minghui Li, Wei Liu, Shengshan Hu, Yechao Zhang, Wei Wan, Lulu Xue, Leo Yu Zhang, Dezhong Yao, and Hai Jin. Securely Fine-Tuning Pre-trained Encoders Against Adversarial Examples. IEEE Symposium on Security and Privacy (S&P), 2024. (CCF A)
18. Jianrong Lu, Shengshan Hu, Wei Wan, Minghui Li, Leo Yu Zhang, Lulu Xue, and Hai Jin. Depriving the Survival Space of Adversaries against Poisoned Gradients in Federated Learning. IEEE Transactions on Information Forensics and Security (TIFS), 2024. (CCF A)
19. 万伟, 胡胜山, 陆建荣, 李明慧, 周子淇, 金海. 联邦学习在高度数据异构场景下的泛化鲁棒性增强. 中国科学：信息科学, 2024. (CCF A)
20. Wei Wan, Shengshan Hu, Minghui Li, Jianrong Lu, Longling Zhang, Leo Yu Zhang, and Hai Jin. A Four-Pronged Defense against Byzantine Attacks in Federated Learning. Proceedings of the 31st ACM International Conference on Multimedia (ACM MM), 2023. (CCF A)
21. Wei Wan, Shengshan Hu, Jianrong Lu, Leo Yu Zhang, Hai Jin, and Yuanyuan He. Shielding Federated Learning: Robust Aggregation with Adaptive Client Selection. International Joint Conference on Artificial Intelligence (IJCAI), 2022. (CCF A)
專利
1. 胡勝山, 王江雄, 李明慧, 宋梅斌, 張業超, 萬偉. 一種基于SECA 的多尺度網絡及其訓練方法. 中國, 發明專利, 申請號: 2023107551729
2. 胡勝山, 陸建榮, 李明慧, 史俊玉, 萬偉. 一種聯邦學習場景下防禦拜占庭攻擊的方法和系統. 中國, 發明專利, 申請號: 2023103085049
3. 胡勝山, 李明慧, 王乙臣, 薛潞潞, 萬偉, 張業超. 一種協作學習場景下基于符號翻轉的隱私保護方法和系統. 中國, 發明專利, 申請號: 2023111327637
4. 胡勝山, 劉威, 李明慧, 萬偉. 一種基于3D點雲魯棒一致性的後門黑盒檢測方法和系統. 中國, 發明專利, 申請號: 2023109302970
學術獎項
1. 博士研究生國家獎學金 2024
2. 華中科技大學科技創新獎學金 2024
3. 華中科技大學優秀畢業生 2025
4. 華中科技大學知行獎學金 2022
5. 華中科技大學三好研究生 2022&2024
6. “華爲杯”第二届中國研究生網絡安全創新大賽三等獎 2023
7. 第七、八、九届全國大學生數學競賽一等獎 2015、2016、2017
8. 第四、五、六届湖北省大學生數學競賽一等獎 2015、2016、2017
9. 第八届藍橋杯全國軟件和信息技術專業人才大賽二等獎 2017
科研項目：
1. 澳門科學技術發展基金，面向物理世界的具身智能安全技術研究，主持。（2026-2028）
2. 国家自然科学基金（面上项目），大规模预训练模型安全基础理论与技术研究 （No. 62372196），参与。（2024-2028）
3. 国家自然科学基金（联合基金），自动驾驶智能系统对抗攻击与安全防护 （No. U20A20177），参与。（2020-2025）
4. 国家自然科学基金（青年基金），基于联邦学习的多模态数据安全查询技术研究（No. 62002126），参与。（2021-2024）
5. 网络安全学院学生创新资助项目，联邦学习Secure Aggregation问题，主持。（2022-2023）
6. 网络安全学院学生创新资助项目，联邦学习安全攻防，主持。（2024-2025）
