利用梯度偏斜规避联邦学习中的拜占庭防御
Exploit Gradient Skewness to Circumvent Byzantine Defenses for Federated Learning
AI总结：
本文发现联邦学习中因数据异构导致的梯度偏斜现象，提出STRIKE攻击利用该现象使拜占庭梯度隐藏于密集分布的偏斜梯度中，从而规避现有拜占庭防御，实验验证了其有效性。
摘要：
联邦学习（FL）因易受拜占庭攻击而闻名。当前大多数拜占庭防御共享一个共同的归纳偏置：在所有梯度中，分布密集的梯度更可能是诚实的。然而，由于本文新发现的梯度偏斜现象，这种偏置对拜占庭鲁棒性而言是一种隐患。我们发现，由于数据异构性，一组分布密集的诚实梯度会偏离最优梯度（诚实梯度的平均值）。这种梯度偏斜现象使拜占庭梯度能隐藏在分布密集的偏斜梯度中，导致拜占庭防御误将拜占庭梯度视为诚实梯度。基于这一观察，我们提出一种新型偏斜感知攻击STRIKE：首先搜索偏斜梯度，然后在偏斜梯度内构造拜占庭梯度。在三个基准数据集上的实验验证了该攻击的有效性。
英文摘要：
Federated Learning (FL) is notorious for its vulnerability to Byzantine attacks. Most current Byzantine defenses share a common inductive bias: among all the gradients, the densely distributed ones are more likely to be honest. However, such a bias is a poison to Byzantine robustness due to a newly discovered phenomenon in this paper - gradient skew. We discover that a group of densely distributed honest gradients skew away from the optimal gradient (the average of honest gradients) due to heterogeneous data. This gradient skew phenomenon allows Byzantine gradients to hide within the densely distributed skewed gradients. As a result, Byzantine defenses are confused into believing that Byzantine gradients are honest. Motivated by this observation, we propose a novel skew-aware attack called STRIKE: first, we search for the skewed gradients; then, we construct Byzantine gradients within the skewed gradients. Experiments on three benchmark datasets validate the effectiveness of our attack
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。
