带联邦防御的SignSGD：通过梯度符号解码利用对抗攻击
SignSGD with Federated Defense: Harnessing Adversarial Attacks through Gradient Sign Decoding
AI总结：
针对分布式学习中一比特量化优化器signSGD-MV在对抗攻击下收敛速度下降的问题，提出带联邦防御的signSGD-FD，通过梯度符号解码加权利用对抗节点梯度，在对抗节点少于良性节点时收敛速度不受影响，且多种攻击场景下优于传统算法。
摘要：
分布式学习是利用多个工作节点加速模型训练的有效方法。然而，由于梯度通信相关的巨大成本，工作节点与参数服务器之间会出现严重的通信延迟。带多数投票的SignSGD（signSGD-MV）是一种简单有效的优化器，通过一比特量化降低通信成本，但随着对抗性工作节点数量增加，其收敛速度会大幅下降。本文证明，只要对抗性工作节点的数量少于良性工作节点，收敛速度不会随对抗性工作节点数量增加而变化。得出这一反直觉结果的核心思路是我们提出的新型带联邦防御的SignSGD（signSGD-FD）。与传统方法不同，signSGD-FD通过梯度符号解码获得合适权重，利用对抗性工作节点发送的梯度信息。实验结果表明，在多种对抗攻击场景下，signSGD-FD的收敛速度优于传统算法。
英文摘要：
Distributed learning is an effective approach to accelerate model training using multiple workers. However, substantial communication delays emerge between workers and a parameter server due to massive costs associated with communicating gradients. SignSGD with majority voting (signSGD-MV) is a simple yet effective optimizer that reduces communication costs through one-bit quantization, yet the convergence rates considerably decrease as adversarial workers increase. In this paper, we show that the convergence rate is invariant as the number of adversarial workers increases, provided that the number of adversarial workers is smaller than that of benign workers. The key idea showing this counter-intuitive result is our novel signSGD with federated defense (signSGD-FD). Unlike the traditional approaches, signSGD-FD exploits the gradient information sent by adversarial workers with the proper weights, which are obtained through gradient sign decoding. Experimental results demonstrate signSGD-FD achieves superior convergence rates over traditional algorithms in various adversarial attack scenarios.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
