Exploit Gradient Skewness to Circumvent Byzantine Defenses for Federated Learning
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
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningInductive BiasSimilar Papers 제목 키워드 기반
Linear Scalarization for Byzantine-robust learning on non-IID data
In this work we study the problem of Byzantine-robust learning when data among clients is heterogeneous. We focus on poisoning attacks targeting the convergence of SGD. Although this problem has received great attention;…
BOBA: Byzantine-Robust Federated Learning with Label Skewness
In federated learning, most existing robust aggregation rules (AGRs) combat Byzantine attacks in the IID setting, where client data is assumed to be independent and identically distributed. In this paper, we address labe…
Federated LearningSelection biasByzantine-Robust Learning on Heterogeneous Datasets via Bucketing
In Byzantine robust distributed or federated learning, a central server wants to train a machine learning model over data distributed across multiple workers. However, a fraction of these workers may deviate from the pre…
Distributed OptimizationFederated LearningObfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
We identify obfuscated gradients, a kind of gradient masking, as a phenomenon that leads to a false sense of security in defenses against adversarial examples. While defenses that cause obfuscated gradients appear to def…
Adversarial AttackAdversarial DefenseByzantine-Robust Learning on Heterogeneous Datasets via Resampling
In Byzantine-robust distributed optimization, a central server wants to train a machine learning model over data distributed across multiple workers. However, a fraction of these workers may deviate from the prescribed a…
Distributed Optimization