# Bayesian Robust Aggregation for Federated Learning

Source: [Bayesian Robust Aggregation for Federated Learning](<https://www.sota2.com/research/paper/68fa78661e209131cea783b6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:16.117Z

Authors: Aleksandr Karakulev, Usama Zafar, Salman Toor, Prashant Singh (1 and 3) \_\_INSTITUTION\_4\_\_ Uppsala University, (2) Scaleout Systems, (3) Science for Life Laboratory, Sweden)

Published: 2025-05-05T09:16:43.000Z

## Abstract

Federated Learning enables collaborative training of machine learning models on decentralized data. This scheme, however, is vulnerable to adversarial attacks, when some of the clients submit corrupted model updates. In real-world scenarios, the total number of compromised clients is typically unknown, with the extent of attacks potentially varying over time. To address these challenges, we propose an adaptive approach for robust aggregation of model updates based on Bayesian inference. The mean update is defined by the maximum of the likelihood marginalized over probabilities of each client to be \`honest'. As a result, the method shares the simplicity of the classical average estimators (e.g., sample mean or geometric median), being independent of the number of compromised clients. At the same time, it is as effective against attacks as methods specifically tailored to Federated Learning, such as Krum. We compare our approach with other aggregation schemes in federated setting on three benchmark image classification data sets. The proposed method consistently achieves state-of-the-art performance across various attack types with static and varying number of malicious clients.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.02490>)

[PDF](<https://arxiv.org/pdf/2505.02490.pdf>)
