对抗梯度重建攻击的优化防御

Nov, 2024

Optimal Defenses Against Gradient Reconstruction Attacks

Yuxiao Chen, Gamze Gürsoy, Qi Lei

TL;DR本研究解决了联邦学习中梯度重建攻击导致的数据泄露问题。文章提出了一种新的防御方法，通过推导重建误差的理论下界，并定制噪声添加和梯度剪枝策略，以优化数据泄露与模型效用的平衡。实验结果表明，所提出的方法在保护训练数据的同时，实现了更优的模型效用。

Abstract

Federated Learning (FL) is designed to prevent Data Leakage through collaborative model training without centralized data storage. However, it remains vulnerable to →