BriefGPT.xyz
Feb, 2022
通过梯度放大在大批量联邦学习中收集用户数据
Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification
HTML
PDF
Yuxin Wen, Jonas Geiping, Liam Fowl, Micah Goldblum, Tom Goldstein
TL;DR
本文介绍了一种新的策略，能够在批处理任意大小和不需要架构修改的情况下，在交叉设备和交叉硅质联邦学习中提取高保真数据，通过修改发送给用户的模型参数来在现实威胁模型中实现。
Abstract
federated learning
(FL) has rapidly risen in popularity due to its promise of privacy and efficiency. Previous works have exposed
privacy vulnerabilities
in the FL pipeline by recovering user data from
→