BriefGPT.xyz
Aug, 2024
通过残差扰动进行数据隐私保护的深度学习
Deep Learning with Data Privacy via Residual Perturbation
HTML
PDF
Wenqi Tao, Huaming Ling, Zuoqiang Shi, Bao Wang
TL;DR
本研究针对深度学习中的数据隐私问题，提出了一种基于随机微分方程的残差扰动方法，能够有效保护隐私同时减小实用性损失。通过理论证明和实证研究，我们展示了该方法不仅保证了差分隐私，还在效率和实用性上优于现有的主流不同ially私有随机梯度下降算法。
Abstract
Protecting
Data Privacy
in
Deep Learning
(DL) is of crucial importance. Several celebrated privacy notions have been established and used for privacy-preserving DL. However, many existing mechanisms achieve priva
→