Beyond Trade-offs: A Unified Framework for Privacy, Robustness, and Communication Efficiency in Federated Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xia, Yue, Jahani-Nezhad, Tayyebeh, Bitar, Rawad
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909975660462080
author Xia, Yue
Jahani-Nezhad, Tayyebeh
Bitar, Rawad
author_facet Xia, Yue
Jahani-Nezhad, Tayyebeh
Bitar, Rawad
contents We propose Fed-DPRoC, a novel federated learning framework designed to jointly provide differential privacy (DP), Byzantine robustness, and communication efficiency. Central to our approach is the concept of robust-compatible compression, which allows reducing the bi-directional communication overhead without undermining the robustness of the aggregation. We instantiate our framework as RobAJoL, which integrates the Johnson-Lindenstrauss (JL)-based compression mechanism with robust averaging for robustness. Our theoretical analysis establishes the compatibility of JL transform with robust averaging, ensuring that RobAJoL maintains robustness guarantees, satisfies DP, and substantially reduces communication overhead. We further present simulation results on CIFAR-10, Fashion MNIST, and FEMNIST, validating our theoretical claims. We compare RobAJoL with a state-of-the-art communication-efficient and robust FL scheme augmented with DP for a fair comparison, demonstrating that RobAJoL outperforms existing methods in terms of robustness and utility under different Byzantine attacks.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12978
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Trade-offs: A Unified Framework for Privacy, Robustness, and Communication Efficiency in Federated Learning
Xia, Yue
Jahani-Nezhad, Tayyebeh
Bitar, Rawad
Machine Learning
Distributed, Parallel, and Cluster Computing
Information Theory
We propose Fed-DPRoC, a novel federated learning framework designed to jointly provide differential privacy (DP), Byzantine robustness, and communication efficiency. Central to our approach is the concept of robust-compatible compression, which allows reducing the bi-directional communication overhead without undermining the robustness of the aggregation. We instantiate our framework as RobAJoL, which integrates the Johnson-Lindenstrauss (JL)-based compression mechanism with robust averaging for robustness. Our theoretical analysis establishes the compatibility of JL transform with robust averaging, ensuring that RobAJoL maintains robustness guarantees, satisfies DP, and substantially reduces communication overhead. We further present simulation results on CIFAR-10, Fashion MNIST, and FEMNIST, validating our theoretical claims. We compare RobAJoL with a state-of-the-art communication-efficient and robust FL scheme augmented with DP for a fair comparison, demonstrating that RobAJoL outperforms existing methods in terms of robustness and utility under different Byzantine attacks.
title Beyond Trade-offs: A Unified Framework for Privacy, Robustness, and Communication Efficiency in Federated Learning
topic Machine Learning
Distributed, Parallel, and Cluster Computing
Information Theory
url https://arxiv.org/abs/2508.12978