Saved in:
Bibliographic Details
Main Authors: Wang, Haodi, Jiang, Tangyu, Guo, Yu, Cai, Chengjun, Wang, Cong, Jia, Xiaohua
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.11663
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Deep learning models have been extensively adopted in various regions due to their ability to represent hierarchical features, which highly rely on the training set and procedures. Thus, protecting the training process and deep learning algorithms is paramount in privacy preservation. Although Differential Privacy (DP) as a powerful cryptographic primitive has achieved satisfying results in deep learning training, the existing schemes still fall short in preserving model utility, i.e., they either invoke a high noise scale or inevitably harm the original gradients. To address the above issues, in this paper, we present a more robust and provably secure approach for differentially private training called GReDP. Specifically, we compute the model gradients in the frequency domain and adopt a new approach to reduce the noise level. Unlike previous work, our GReDP only requires half of the noise scale compared to DPSGD [1] while keeping all the gradient information intact. We present a detailed analysis of our method both theoretically and empirically. The experimental results show that our GReDP works consistently better than the baselines on all models and training settings.