Understanding Byzantine Robustness in Federated Learning with A Black-box Server
Not on the map. Why?
Abstract (arXiv)
Federated learning (FL) becomes vulnerable to Byzantine attacks where some of participators tend to damage the utility or discourage the convergence of the learned model via sending their malicious model updates. Previous works propose to apply robust rules to aggregate updates from participators against different types of Byzantine attacks, while at the same time, attackers can further design advanced Byzantine attack algorithms targeting specific aggregation rule when it is known. In practice, FL systems can involve a black-box server that makes the adopted aggregation rule inaccessible to participants, which can naturally defend or weaken some Byzantine attacks. In this paper, we provide an in-depth understanding on the Byzantine robustness of the FL system with a black-box server. Our investigation demonstrates the improved Byzantine robustness of a black-box server employing a dynamic defense strategy. We provide both empirical evidence and theoretical analysis to reveal that the black-box server can mitigate the worst-case attack impact from a maximum level to an expectation level, which is attributed to the inherent inaccessibility and randomness offered by a black-box server.The source code is available at https://github.com/alibaba/FederatedScope/tree/Byzantine_attack_defense to promote further research in the community.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 28 of its 37 references that are in the map. First posted on arXiv 12 Aug 2024.
Builds on
28 of 37 references.
References · 28
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2019Advances and Open Problems in Federated Learningcited by 3,021
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
- 2019Towards Federated Learning at Scale: System Designcited by 826
- 2018LEAF: A Benchmark for Federated Settingscited by 780
- 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
- 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
- 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
- 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
- 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
16 more
- 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
- 2018Mitigating Sybils in Federated Learning Poisoningcited by 158
- 2020Learning from History for Byzantine Robust Optimizationcited by 137
- 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
- 2022Byzantine Machine Learning Made Easy by Resilient Averaging of Momentumscited by 63
- 2019Zeno++: Robust Fully Asynchronous SGDcited by 53
- 2019Abnormal Client Behavior Detection in Federated Learningcited by 39
- 2020Randomization matters. How to defend against strong adversarial attackscited by 37
- 2021Mixed Nash Equilibria in the Adversarial Examples Gamecited by 22
- 2022Shielding Federated Learning: Robust Aggregation with Adaptive Client Selectioncited by 18
- 2023Byzantine-Robust Learning on Heterogeneous Data via Gradient Splittingcited by 13
- 2022MixTailor: Mixed Gradient Aggregation for Robust Learning Against Tailored Attackscited by 5
- 2024Belt and Braces: When Federated Learning Meets Differential Privacycited by 4
- 2020Latent Dirichlet Allocation Model Training with Differential Privacycited by 3
Built on by
Citing papers per year: 2025: 1.
1 paper.