葉大庸 博士

副教授(研究) 博導/碩導
電子郵箱:dyye@cityu.edu.mo
電話:(853)85902336
辦公地址:澳門城市大學(氹仔)何鴻燊樓S504室
學歷
2013 計算機科學博士,臥龍崗大學,澳大利亞
2009 計算機科學碩士,臥龍崗大學,澳大利亞
2003 機電一體化學士,合肥工業大學,中國
現任
澳門城市大學數據科學學院副教授(研究)
研究方向
人工智能隱私保護,多智能體系統安全
研究及出版
- Dayong Ye, T Zhu, F He, B Liu, M Xue and W Zhou, “Cross-Modal Prompt Inversion: Unifying Threats to Text and Image Generative AI Models”, Proc. of USENIX Security Symposium, 2025. (CCF A)
- Dayong Ye, T Zhu, S Wang, B Liu, L Y Zhang, W Zhou and Y Zhang, “Data-Free Model-Related Attacks: Unleashing the Potential of Generative AI”, Proc. of USENIX Security Symposium, 2025. (CCF A)
- Dayong Ye, T Zhu, J Li, K Gao, B Liu, L Y Zhang, W Zhou and Y Zhang, “Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearning”, Proc. of USENIX Security Symposium, 2025. (CCF A)
- Dayong Ye, T Zhu, C Zhu, D Wang, K Gao, Z Shi, S Shen, W Zhou and M Xue, “Reinforcement Unlearning”, Proc. of NDSS Symposium, 2025. (CCF A)
- Dayong Ye, H Chen, S Zhou, T Zhu, W Zhou, S Ji, “Model Inversion Attack Against Transfer Learning: Inverting a Model Without Querying It”, IEEE Transactions on Dependable and Secure Computing, 2025. (CCF A, JCR Q1)
- Dayong Ye, T Zhu, K Gao, C Zhu, and W Zhou, “Cooperating or Kicking Out: Defending against Poisoning Attacks in Federated Learning via the Evolution of Cooperation”, IEEE Transactions on Dependable and Secure Computing, 2025. (CCF A, JCR Q1)
- Dayong Ye, T Zhu, K Gao and W Zhou, “Defending against Label-only Attacks via Meta-Reinforcement Learning”, IEEE Transactions on Information Forensics and Security, 2024. (CCF A, JCR Q1)
- T Zhu, Dayong Ye, Z Cheng, W Zhou, S Y Philip, “Learning Games for Defending Advanced Persistent Threats in Cyber Systems”, IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 53, no. 4, pp. 2410-2422, 2023. (JCR Q1)
- T Zhu, Dayong Ye, S Zhou, B Liu, W Zhou, “Label-only Model Inversion Attacks: Attack with the Least Information”, IEEE Transactions on Information Forensics and Security, vol. 18, pp. 991-1005, 2023. (CCF A, JCR Q1)
- Dayong Ye, T Zhu, C Zhu, W Zhou, SY Philip, “Model-Based Self-Advising for Multi-Agent Learning”, IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 10, pp. 7934-7945, 2023. (JCR Q1)
- Dayong Ye, S Shen, T Zhu, B Liu, W Zhou, “One Parameter DefenseDefending Against Data Inference Attacks via Differential Privacy”, IEEE Transactions on Information Forensics and Security, vol. 17, pp.1466-1480, 2022. (CCF A, JCR Q1)
- Dayong Ye, T Zhu, Z Cheng, W Zhou and P S Yu, “Differential Advising in Multi-Agent Reinforcement Learning”, IEEE Transactions on Cybernetics, vol. 52, no. 6, pp. 5508-5521, 2022. (JCR Q1)
- Dayong Ye, T Zhu, S Shen, W Zhou and P S Yu,“Differentially Private Multi-Agent Planning for Logistic-like Problems”, IEEE Transactions on Dependable and Secure Computing, vol. 19, pp. 1212-1226, 2022. (CCF A, JCR Q1)
- T Zhu, Dayong Ye, W Wang, W Zhou and P S Yu, “More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligence”, IEEE Transactions on Knowledge and Data Engineering, vol. 14, no.6, pp. 2824-2843, 2022. (CCF A, JCR Q1)
- S Wang, T Zhu, Dayong Ye, W Zhou, “When machine unlearning meets retrieval-augmented generation (rag): Keep secret or forget knowledge?”, IEEE Transactions on Dependable and Secure Computing, 2025. (CCF A, JCR Q1)
- S Wang, T Zhu, B Liu, M Ding, Dayong Ye, W Zhou, P Yu, “Unique security and privacy threats of large language models: A comprehensive survey”, ACM Computing Surveys, vol. 58, no. 4, pp. 1-36, 2025. (CCF A, JCR Q1)
- S Zhou, Dayong Ye, T Zhu, W Zhou, “Defending Against Neural Network Model Inversion Attacks via Data Poisoning”, IEEE Transactions on Neural Networks and Learning Systems, 2025. (JCR Q1)
- S Zhou, T Zhu, Dayong Ye, X Yu and W Zhou, “Boosting Model Inversion Attacks with Adversarial Examples”, IEEE Transactions on Dependable and Secure Computing, 2023. (CCF A, JCR Q1)
- C Zhu, Z Cheng, Dayong Ye, FK Hussain, T Zhu, and W Zhou, “Time-driven and Privacy-preserving Navigation Model for Vehicle-to-vehicle Communication Systems”, IEEE Transactions on Vehicular Technology, 2023.(JCR Q1)
- S Zhou, C Liu, Dayong Ye, T Zhu, W Zhou, P S Yu, “Adversarial attacks and defenses in deep learning: From a perspective of cybersecurity”, ACM Computing Surveys, vol. 55, no. 8, pp. 1-39, 2022. (CCF A, JCR Q1)
- L Zhang, T Zhu, F K Hussain, Dayong Ye, and W Zhou, “A Game-theoretic Method for Defending against Advanced Persistent Threats in Cyber Systems”, IEEE Transactions on Information Forensics and Security,2022. (CCF A, JCR Q1)
學術獎項
2012 年度國家優秀自費留學生

