A Huber Loss Minimization Approach to Byzantine Robust Federated Learning
Puning Zhao, Fei Yu, Zhiguo Wan
2023-08-24Federated Learning
Abstract
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 $\epsilon$, which stands for the ratio of attacked clients. Secondly, our approach does not need precise knowledge of $\epsilon$. 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.
Related Papers
FedGA: A Fair Federated Learning Framework Based on the Gini Coefficient2025-07-17A Distributed Generative AI Approach for Heterogeneous Multi-Domain Environments under Data Sharing constraints2025-07-17Federated Learning for Commercial Image Sources2025-07-17A Bayesian Incentive Mechanism for Poison-Resilient Federated Learning2025-07-16Federated Learning in Open- and Closed-Loop EMG Decoding: A Privacy and Performance Perspective2025-07-16Safeguarding Federated Learning-based Road Condition Classification2025-07-16Site-Level Fine-Tuning with Progressive Layer Freezing: Towards Robust Prediction of Bronchopulmonary Dysplasia from Day-1 Chest Radiographs in Extremely Preterm Infants2025-07-16Self-Adaptive and Robust Federated Spectrum Sensing without Benign Majority for Cellular Networks2025-07-16