Tre' R. Jeter, Truc Nguyen, Raed Alharbi, My T. Thai
TL;DR本文提出了基于图像增强的防御机制 OASIS,以有效抵抗主动重构攻击,同时保持模型性能。
Abstract
federated learning (FL) has garnered significant attention for its potential
to protect user privacy while enhancing model training efficiency. However,
recent research has demonstrated that FL protocols can be e