Lab Seminar
2024 DP-SGD review Seminar
[Book Reading] Zhu, Tianqing, et al. Differential privacy and applications. Cham, Switzerland: Springer International Publishing, 2017.
[Paper Review] Yu, Lei, et al. "Differentially private model publishing for deep learning." 2019 IEEE symposium on security and privacy (SP). IEEE, 2019.
[Paper Review] Pichapati, Venkatadheeraj, et al. " AdaCliP: Adaptive Clipping for Private SGD " arXiv preprint arXiv:1908.07643 (2019).
[Paper Review] Chen, Xiangyi, Steven Z. Wu, and Mingyi Hong. "Understanding gradient clipping in private SGD: A geometric perspective." Advances in Neural Information Processing Systems 33 (2020): 13773-13782.
[Paper Review] Xu, Zhiying, et al. "An adaptive and fast convergent approach to differentially private deep learning." IEEE INFOCOM 2020-IEEE Conference on Computer Communications. IEEE, 2020.
[Paper Review] Andrew, Galen, et al. "Differentially private learning with adaptive clipping." Advances in Neural Information Processing Systems 34 (2021): 17455-17466.
[Paper Review] Zhang, Xinyue, et al. "Adaptive privacy preserving deep learning algorithms for medical data." Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2021.
[Paper Review] Fang, Huang, et al. "Improved convergence of differential private SGD with gradient clipping." The Eleventh International Conference on Learning Representations. 2022.
[Paper Review] Wei, Jianxin, et al. "Dpis: An enhanced mechanism for differentially private sgd with importance sampling." Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security. 2022.