高坤 博士

助理教授 碩導

電子郵箱：kungao@cityu.edu.mo

學校電話：(853)85902389

辦公地址：澳門城市大學(氹仔)何鴻燊樓S504室

學歷

2026　信息系統博士, 悉尼科技大學, 澳大利亞

2022　信息技術榮譽學士, 悉尼科技大學, 澳大利亞

2018　計算機科學與技術學士, 中國地質大學（武漢）, 武漢

研究方向

聯邦學習（Federated Learning）、機器遺忘（Machine Unlearning）、強化學習（Reinforcement Learning）、隱私保護機器學習（Privacy-Preserving Machine Learning）、大模型安全（LLM Security）

研究及出版

1. Gao, K., Zhu, T., Ye, D., Liu, B., & Zhou, W. (2026). Hidden threats in federated unlearning: Camouflaged poisoning attacks and their unlearning consequences. IEEE Transactions on Dependable and Secure Computing, 23(2), 2934–2948. https://doi.org/10.1109/TDSC.2025.3630811

2. Gao, K., Zhu, T., Ye, D., Gao, L., & Zhou, W. (2025). Federated unlearning with reinforcement learning: Adaptive privacy preservation for clients. Journal of Information Security and Applications, 93, 104164. https://doi.org/10.1016/j.jisa.2025.104164

3. Gao, K., Zhu, T., Ye, D., & Zhou, W. (2024). Defending against gradient inversion attacks in federated learning via statistical machine unlearning. Knowledge-Based Systems, 299, 111983. https://doi.org/10.1016/j.knosys.2024.111983

4. Ye, D., Zhu, T., Zhu, C., Wang, D., Gao, K., Shi, Z., Shen, S., Zhou, W., & Xue, M. (2025). Reinforcement unlearning. In Proceedings of the Network and Distributed System Security Symposium (NDSS 2025). https://doi.org/10.14722/ndss.2025.230080

5. Ye, D., Zhu, T., Gao, K., & Zhou, W. (2024). Defending against label-only attacks via meta-reinforcement learning. IEEE Transactions on Information Forensics and Security. https://doi.org/10.1109/TIFS.2024.3357292

6. Ye, D., Zhu, T., Gao, K., Zhu, C., & Zhou, W. (2025). Cooperating or kicking out: Defending against poisoning attacks in federated learning via the evolution of cooperation. IEEE Transactions on Dependable and Secure Computing. https://doi.org/10.1109/TDSC.2025.3532351

7. Zhang, T., Zhu, T., Gao, K., Zhou, W., & Yu, P. S. (2021). Balancing learning model privacy, fairness, and accuracy with early stopping criteria. IEEE Transactions on Neural Networks and Learning Systems. https://doi.org/10.1109/TNNLS.2021.3129592

8. Ye, D., Zhu, T., Li, J., Gao, K., Liu, B., Zhang, L. Y., Zhou, W., & Zhang, Y. (2025). Data duplication: A novel multi-purpose attack paradigm in machine unlearning. In 34th USENIX Security Symposium (USENIX Security 25) (pp. 6399–6418). USENIX Association.