FedCut: A Spectral Analysis Framework for Reliable Detection of Byzantine Colluders
Not on the map. Why?
Abstract (arXiv)
This paper proposes a general spectral analysis framework that thwarts a security risk in federated Learning caused by groups of malicious Byzantine attackers or colluders, who conspire to upload vicious model updates to severely debase global model performances. The proposed framework delineates the strong consistency and temporal coherence between Byzantine colluders' model updates from a spectral analysis lens, and, formulates the detection of Byzantine misbehaviours as a community detection problem in weighted graphs. The modified normalized graph cut is then utilized to discern attackers from benign participants. Moreover, the Spectral heuristics is adopted to make the detection robust against various attacks. The proposed Byzantine colluder resilient method, i.e., FedCut, is guaranteed to converge with bounded errors. Extensive experimental results under a variety of settings justify the superiority of FedCut, which demonstrates extremely robust model performance (MP) under various attacks. It was shown that FedCut's averaged MP is 2.1% to 16.5% better than that of the state of the art Byzantine-resilient methods. In terms of the worst-case model performance (MP), FedCut is 17.6% to 69.5% better than these methods.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 37 of its 85 references that are in the map. First posted on arXiv 24 Nov 2022.
Builds on
37 of 85 references.
References · 37
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2019Advances and Open Problems in Federated Learningcited by 3,021
- 2016Deep Learning with Differential Privacycited by 2,682
- 2021Convex optimizationcited by 2,479
- 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
- 2019Deep Leakage from Gradientscited by 1,004
- 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
- 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 566
- 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
- 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
- 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
25 more
- 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
- 2019Robust Aggregation for Federated Learningcited by 314
- 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
- 2016Robust Estimators in High Dimensions without the Computational Intractabilitycited by 209
- 2019On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimizationcited by 178
- 2018RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasetscited by 148
- 2020Learning from History for Byzantine Robust Optimizationcited by 137
- 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 136
- 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 125
- 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 116
- 2018Generalized Byzantine-tolerant SGDcited by 94
- 2019Robust Federated Learning in a Heterogeneous Environmentcited by 88
- 2018Byzantine Stochastic Gradient Descentcited by 81
- 2018DRACO: Byzantine-resilient Distributed Training via Redundant Gradientscited by 74
- 2022Byzantine Machine Learning Made Easy by Resilient Averaging of Momentumscited by 63
- 2020Byzantine-Resilient Non-Convex Stochastic Gradient Descentcited by 56
- 2019Zeno++: Robust Fully Asynchronous SGDcited by 53
- 2019DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregationcited by 44
- 2020Byzantine-Resilient High-Dimensional Federated Learningcited by 27
- 2019Communication-Efficient Local Decentralized SGD Methodscited by 21
- 2019Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attackscited by 20
- 2019Byzantine-Resilient Stochastic Gradient Descent for Distributed Learning: A Lipschitz-Inspired Coordinate-wise Median Approachcited by 13
- 2020Byzantine-Robust Decentralized Stochastic Optimization over Static and Time-Varying Networkscited by 10
- 2018Zeno: Distributed Stochastic Gradient Descent with Suspicion-based Fault-tolerancecited by 8
- 2021Byzantine Fault-Tolerance in Federated Local SGD under 2f-Redundancycited by 7
Built on by
Citing papers per year: 2024: 1.
1 paper.