BriefGPT.xyz
May, 2023
数据不可知联邦学习服务器端后门攻击
DABS: Data-Agnostic Backdoor attack at the Server in Federated Learning
HTML
PDF
Wenqiang Sun, Sen Li, Yuchang Sun, Jun Zhang
TL;DR
本文提出了一个新的攻击模型，称为服务器上的数据不可知后门攻击(DABS)，该模型旨在直接修改全局模型以在FL系统中放置后门。
Abstract
federated learning
(FL) attempts to train a
global model
by aggregating local models from distributed devices under the coordination of a central server. However, the existence of a large number of heterogeneous
→