FedSharp: Byzantine Robust Decentralized Federated Learning Under Noisy Channel
Organizations: School of EECS, Ohio University, Athens, OH, USA · School of EECS, University of Ottawa, Ottawa, ON, Canada
Abstract
Decentralized federated learning (DFL) eliminates the central aggregation server but remains vulnerable to non-independent and identically distributed (non-IID) data, Byzantine attacks, and channel noise. We show that channel noise accumulates as models propagate across nodes and becomes increasingly significant as the learning rate decays. Moreover, accumulated noise enables Byzantine attackers to exploit loss-based model selection by mimicking the average of the honest models. To address these challenges, we propose FedSharp (screened, hop-aware, averaged, ranked, proximal), a robust DFL framework. In FedSharp, each node keeps the latest models received from its 2b predecessors, which guarantees at least b honest candidates when at most b nodes are Byzantine. FedSharp screens suspicious models using their deviations from the coordinate-wise median, averages the b lowest-loss candidates to reduce the fresh channel-noise variance by a factor of b, and applies hop-aware gradient-norm regularization and proximal training to mitigate accumulated noise and non-IID drift. Experiments on a 100-node ring with 33 Byzantine nodes show that FedSharp achieves 93.5 to 94.9 percent accuracy on MNIST, compared with 29.4 to 38.1 percent for a state-of-the-art single-model-selection benchmark, and 32.8 to 48.8 percent on CIFAR-10, compared with 10.0 to 30.5 percent, across Gaussian and hidden attacks under IID and non-IID data. On MNIST, FedSharp comes within 1.3 percentage points of the benchmark operating without channel noise, and exceeds it under the hidden attack.
Figures & tables
| Item | Setting |
|---|---|
| Datasets | MNIST, CIFAR-10 |
| Clients / rounds | 100 / 500 ring rounds |
| Partition | IID; non-IID (Dirichlet ) |
| Optimizer | SGD, batch 80, |
| Basil | , 1 step; ACDS shares |
| FedSharp | , , , , , |
Byzantine-Robust Federated Learning
Byzantine-robust federated learning protects collaboratively trained models from clients that send corrupted, poisoned, or strategically manipulated updates.
See all 91 papers