mlsanityData to 7 Oct 2026

Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guarantees

arXiv 2205.11765 ↗First posted 24 May 2022cs.LG cs.AI cs.CRcited by 30

Not on the map. Why?

Abstract (arXiv)

We propose Byzantine-robust federated learning protocols with nearly optimal statistical rates. In contrast to prior work, our proposed protocols improve the dimension dependence and achieve a tight statistical rate in terms of all the parameters for strongly convex losses. We benchmark against competing protocols and show the empirical superiority of the proposed protocols. Finally, we remark that our protocols with bucketing can be naturally combined with privacy-guaranteeing procedures to introduce security against a semi-honest server. The code for evaluation is provided in https://github.com/wanglun1996/secure-robust-federated-learning.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 47 of its 82 references that are in the map. First posted on arXiv 24 May 2022.

Builds on

47 of 82 references.

References · 47

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  4. 2018How To Backdoor Federated Learningcited by 745
  5. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  6. 2014Convex Optimization: Algorithms and Complexitycited by 569
  7. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  8. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  9. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  10. 2019Robust Aggregation for Federated Learningcited by 314
  11. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  12. 2017Certified Defenses for Data Poisoning Attackscited by 288
35 more
  1. 2019Can You Really Backdoor Federated Learning?cited by 250
  2. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  3. 2016Robust Estimators in High Dimensions without the Computational Intractabilitycited by 209
  4. 2018Mitigating Sybils in Federated Learning Poisoningcited by 158
  5. 2020Learning from History for Byzantine Robust Optimizationcited by 137
  6. 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 136
  7. 2016Agnostic Estimation of Mean and Covariancecited by 131
  8. 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 125
  9. 2018Sever: A Robust Meta-Algorithm for Stochastic Optimizationcited by 123
  10. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 105
  11. 2020Byzantine-Resilient Secure Federated Learningcited by 93
  12. 2017Being Robust (in High Dimensions) Can Be Practicalcited by 83
  13. 2018Byzantine Stochastic Gradient Descentcited by 81
  14. 2018Efficient Algorithms and Lower Bounds for Robust Linear Regressioncited by 76
  15. 2018DRACO: Byzantine-resilient Distributed Training via Redundant Gradientscited by 74
  16. 2020Data Poisoning Attacks on Federated Machine Learningcited by 58
  17. 2020Byzantine-Resilient Non-Convex Stochastic Gradient Descentcited by 56
  18. 2020Outlier Robust Mean Estimation with Subgaussian Rates via Stabilitycited by 50
  19. 2017Sub-Gaussian estimators of the mean of a random vectorcited by 47
  20. 2020Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimizationcited by 44
  21. 2017Resilience: A Criterion for Learning in the Presence of Arbitrary Outlierscited by 43
  22. 2019Quantum Entropy Scoring for Fast Robust Mean Estimation and Improved Outlier Detectioncited by 41
  23. 2019Attack-Resistant Federated Learning with Residual-based Reweightingcited by 40
  24. 2018High-Dimensional Robust Mean Estimation in Nearly-Linear Timecited by 39
  25. 2019Generalized Resilience and Robust Statisticscited by 37
  26. 2018Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learningcited by 32
  27. 2020Byzantine-Resilient High-Dimensional Federated Learningcited by 27
  28. 2020Robust estimation via generalized quasi-gradientscited by 19
  29. 2020Secure Byzantine-Robust Machine Learningcited by 18
  30. 2019Deconstructing Generative Adversarial Networkscited by 15
  31. 2020Backdoor Attacks on Federated Meta-Learningcited by 14
  32. 2021Secure Byzantine-Robust Distributed Learning via Clusteringcited by 12
  33. 2019Generative Adversarial Nets for Robust Scatter Estimation: A Proper Scoring Rule Perspectivecited by 8
  34. 2019Nearly Tight Bounds for Robust Proper Learning of Halfspaces with a Margincited by 8
  35. 2018Robust Estimation and Generative Adversarial Netscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 9; 2024: 7; 2025: 8; 2026: 5.

30 papers.

Sort:

By area:

  1. 2023Practical Differentially Private and Byzantine-resilient Federated Learningcited by 18
  2. 2024Provably Unlearnable Data Examplescited by 18
  3. 2023A Huber Loss Minimization Approach to Byzantine Robust Federated Learningcited by 16
  4. 2024Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updatescited by 13
  5. 2023High Dimensional Distributed Gradient Descent with Arbitrary Number of Byzantine Attackerscited by 7
  6. 2025S2FGL: Spatial Spectral Federated Graph Learningcited by 7
  7. 2025FedSV: Byzantine-Robust Federated Learning via Shapley Valuecited by 6
  8. 2022MixTailor: Mixed Gradient Aggregation for Robust Learning Against Tailored Attackscited by 5
  9. 2024On the Byzantine-Resilience of Distillation-Based Federated Learningcited by 5
  10. 2024Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clientscited by 5
  11. 2023Near-Optimal Resilient Aggregation Rules for Distributed Learning Using 1-Center and 1-Mean Clustering with Outlierscited by 4
  12. 2024A survey on secure decentralized optimization and learningcited by 4
18 more
  1. 2024Review of Mathematical Optimization in Federated Learningcited by 3
  2. 2025Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participationcited by 3
  3. 2023WW-FL: Secure and Private Large-Scale Federated Learningcited by 2
  4. 2024TernaryVote: Differentially Private, Communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Datacited by 2
  5. 2025Tight Stability Bounds for Robust Distributed Learning: Byzantine Failures Hurt Generalization More than Data Poisoningcited by 2
  6. 2023Exploring the Robustness of Decentralized Training for Large Language Modelscited by 1
  7. 2023Attacking Byzantine Robust Aggregation in High Dimensionscited by 1
  8. 2023Harnessing the Power of Federated Learning in Federated Contextual Banditscited by 1
  9. 2025Distributionally Robust Federated Learning with Outlier Resiliencecited by 1
  10. 2025A Nesterov-Accelerated Byzantine-Robust Federated Learningcited by 1
  11. 2026When More Data Doesn't Help: Limits of Adaptation in Multitask Learningcited by 1
  12. 2023Byzantine-Robust Clustered Federated Learningcited by 0
  13. 2025FedVSR: Towards Model-Agnostic Federated Learning in Video Super-Resolutioncited by 0
  14. 2025Financial Data Analysis with Robust Federated Logistic Regressioncited by 0
  15. 2026mathsfVISTA: Decentralized Machine Learning in Adversary Dominated Environmentscited by 0
  16. 2026Online Security Learning in Cooperative Multi-Agent Systems under Hidden Byzantine Attackscited by 0
  17. 2026On the Gradient Heterogeneity Dynamics of Adversarially Robust Federated Regressioncited by 0
  18. 2026Robustifying Asynchronous SGD via Soft Throttlingcited by 0