mlsanityData to 14 Oct 2026

A Huber Loss Minimization Approach to Byzantine Robust Federated Learning

arXiv 2308.12581 ↗First posted 24 Aug 2023cs.LG cs.AIcited by 16

Not on the map. Why?

Abstract (arXiv)

Federated learning systems are susceptible to adversarial attacks. To combat this, we introduce a novel aggregator based on Huber loss minimization, and provide a comprehensive theoretical analysis. Under independent and identically distributed (i.i.d) assumption, our approach has several advantages compared to existing methods. Firstly, it has optimal dependence on ε, which stands for the ratio of attacked clients. Secondly, our approach does not need precise knowledge of ε. Thirdly, it allows different clients to have unequal data sizes. We then broaden our analysis to include non-i.i.d data, such that clients have slightly different distributions.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 18 of its 33 references that are in the map. First posted on arXiv 24 Aug 2023.

Builds on

18 of 33 references.

References · 18

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2018How To Backdoor Federated Learningcited by 765
  4. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  5. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  6. 2019Robust Aggregation for Federated Learningcited by 317
  7. 2016Robust Estimators in High Dimensions without the Computational Intractabilitycited by 209
  8. 2018RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasetscited by 149
  9. 2019Robust Federated Learning in a Heterogeneous Environmentcited by 90
  10. 2017Being Robust (in High Dimensions) Can Be Practicalcited by 83
  11. 2019Federated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attackscited by 79
  12. 2016Geometric Median in Nearly Linear Timecited by 39
6 more
  1. 2022Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guaranteescited by 30
  2. 2020List-Decodable Mean Estimation in Nearly-PCA Timecited by 17
  3. 2019How Hard Is Robust Mean Estimation?cited by 16
  4. 2023Robust Nonparametric Regression under Poisoning Attackcited by 11
  5. 2023High Dimensional Distributed Gradient Descent with Arbitrary Number of Byzantine Attackerscited by 7
  6. 2018Securing Distributed Gradient Descent in High Dimensional Statistical Learningcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 8; 2025: 2; 2026: 6.

16 papers.

Sort:

  1. 2024Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challengescited by 15
  2. 2024A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacycited by 11
  3. 2024Federated Learning Resilient to Byzantine Attacks and Data Heterogeneitycited by 4
  4. 2024Learning with User-Level Local Differential Privacycited by 3
  5. 2024Developing Cryptocurrency Trading Strategy Based on Autoencoder-CNN-GANs Algorithmscited by 3
  6. 2025SketchAgent: Generating Structured Diagrams from Hand-Drawn Sketchescited by 3
  7. 2024Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradientscited by 2
  8. 2024Differential Private Stochastic Optimization with Heavy-tailed Data: Towards Optimal Ratescited by 1
  9. 2024FedSECA: Sign Election and Coordinate-wise Aggregation of Gradients for Byzantine Tolerant Federated Learningcited by 0
  10. 2025Coded Robust Aggregation for Distributed Learning under Byzantine Attackscited by 0
  11. 2026FedIDM: Achieving Fast and Stable Convergence in Byzantine Federated Learning through Iterative Distribution Matchingcited by 0
  12. 2026Byzantine-Robust Distributed Sparse Learning Revisitedcited by 0
4 more
  1. 2026Dimensionality Reduction for Robust Federated Learning: A Theoretical Analysis and Convergence Guaranteecited by 0
  2. 2026Enhanced Byzantine-Robust Federated Learning Via Truncated-Quadratic Loss for Heterogeneous Datacited by 0
  3. 2026Median-of-Means as an Extremal Convex Estimator and a Nonconvex Route to the Trimmed Oraclecited by 0
  4. 2026Upholding Robustness in Federated Learning: Trends, Emerging Strategies, and Research Opportunitiescited by 0