Private Aggregation for Byzantine-Resilient Heterogeneous Federated Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Egger, Maximilian, Bitar, Rawad
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909646112948224
author Egger, Maximilian
Bitar, Rawad
author_facet Egger, Maximilian
Bitar, Rawad
contents Ensuring resilience to Byzantine clients while maintaining the privacy of the clients' data is a fundamental challenge in federated learning (FL). When the clients' data is homogeneous, suitable countermeasures were studied from an information-theoretic perspective utilizing secure aggregation techniques while ensuring robust aggregation of the clients' gradients. However, the countermeasures used fail when the clients' data is heterogeneous. Suitable pre-processing techniques, such as nearest neighbor mixing, were recently shown to enhance the performance of those countermeasures in the heterogeneous setting. Nevertheless, those pre-processing techniques cannot be applied with the introduced privacy-preserving mechanisms. We propose a multi-stage method encompassing a careful co-design of verifiable secret sharing, secure aggregation, and a tailored symmetric private information retrieval scheme to achieve information-theoretic privacy guarantees and Byzantine resilience under data heterogeneity. We evaluate the effectiveness of our scheme on a variety of attacks and show how it outperforms the previously known techniques. Since the communication overhead of secure aggregation is non-negligible, we investigate the interplay with zero-order estimation methods that reduce the communication cost in state-of-the-art FL tasks and thereby make private aggregation scalable.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09870
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Private Aggregation for Byzantine-Resilient Heterogeneous Federated Learning
Egger, Maximilian
Bitar, Rawad
Machine Learning
Distributed, Parallel, and Cluster Computing
Information Theory
Ensuring resilience to Byzantine clients while maintaining the privacy of the clients' data is a fundamental challenge in federated learning (FL). When the clients' data is homogeneous, suitable countermeasures were studied from an information-theoretic perspective utilizing secure aggregation techniques while ensuring robust aggregation of the clients' gradients. However, the countermeasures used fail when the clients' data is heterogeneous. Suitable pre-processing techniques, such as nearest neighbor mixing, were recently shown to enhance the performance of those countermeasures in the heterogeneous setting. Nevertheless, those pre-processing techniques cannot be applied with the introduced privacy-preserving mechanisms. We propose a multi-stage method encompassing a careful co-design of verifiable secret sharing, secure aggregation, and a tailored symmetric private information retrieval scheme to achieve information-theoretic privacy guarantees and Byzantine resilience under data heterogeneity. We evaluate the effectiveness of our scheme on a variety of attacks and show how it outperforms the previously known techniques. Since the communication overhead of secure aggregation is non-negligible, we investigate the interplay with zero-order estimation methods that reduce the communication cost in state-of-the-art FL tasks and thereby make private aggregation scalable.
title Private Aggregation for Byzantine-Resilient Heterogeneous Federated Learning
topic Machine Learning
Distributed, Parallel, and Cluster Computing
Information Theory
url https://arxiv.org/abs/2506.09870