Score: 0

Fed-DPRoC:Communication-Efficient Differentially Private and Robust Federated Learning

Published: August 18, 2025 | arXiv ID: 2508.12978v1

By: Yue Xia, Tayyebeh Jahani-Nezhad, Rawad Bitar

Potential Business Impact:

Keeps private data safe during learning.

We propose Fed-DPRoC, a novel federated learning framework that simultaneously ensures differential privacy (DP), Byzantine robustness, and communication efficiency. We introduce the concept of robust-compatible compression, which enables users to compress DP-protected updates while maintaining the robustness of the aggregation rule. We instantiate our framework as RobAJoL, combining the Johnson-Lindenstrauss (JL) transform for compression with robust averaging for robust aggregation. We theoretically prove the compatibility of JL transform with robust averaging and show that RobAJoL preserves robustness guarantees, ensures DP, and reduces communication cost. Experiments on CIFAR-10 and Fashion MNIST validate our theoretical claims and demonstrate that RobAJoL outperforms existing methods in terms of robustness and utility under different Byzantine attacks.

Page Count
10 pages

Category
Computer Science:
Machine Learning (CS)