- 🔭 I’m currently working on AI security, particularly Model Inversion Attacks (MIA)
- 🌱 I’m currently persuing my Ph.D. degree on Cyber Science and Engineering in Southeast University, China.
- 📫 How to reach me: zhangzp9970@outlook.com
- 👯 I’m looking to collaborate on torchplus and making differences!
- 😄 Pronouns: zzp
- ✒️ Motto: Independent of Sprit, Free of Mind. (独立之精神，自由之思想。)
- Z. Zhang, X. Wang, J. Huang, and S. Zhang, “Analysis and Utilization of Hidden Information in Model Inversion Attacks,” IEEE Transactions on Information Forensics and Security, vol. 18, pp. 4449–4462, 2023, doi: 10.1109/TIFS.2023.3295942. [Code]
- S. Zhang, J. Huang, Z. Zhang, and C. Qi, “Compromise Privacy in Large-Batch Federated Learning via Malicious Model Parameters,” in Algorithms and Architectures for Parallel Processing, W. Meng, R. Lu, G. Min, and J. Vaidya, Eds., in Lecture Notes in Computer Science. Cham: Springer Nature Switzerland, 2023, pp. 63–80. doi: 10.1007/978-3-031-22677-9_4. [Code]
- S. Zhang, J. Huang, Z. Zhang, P. Li, and C. Qi, “Compromise privacy in large-batch Federated Learning via model poisoning,” Information Sciences, vol. 647, p. 119421, Nov. 2023, doi: 10.1016/j.ins.2023.119421. [Code]
- C. Liang, J. Huang, Z. Zhang, and S. Zhang, “Defending against model extraction attacks with OOD feature learning and decision boundary confusion,” Computers & Security, vol. 136, p. 103563, Jan. 2024, doi: 10.1016/j.cose.2023.103563.
- P. Li, J. Huang, H. Wu, Z. Zhang, and C. Qi, “SecureNet: Proactive intellectual property protection and model security defense for DNNs based on backdoor learning,” Neural Networks, p. 106199, Feb. 2024, doi: 10.1016/j.neunet.2024.106199.