Computational Code-Based Privacy in Coded Federated Learning

TL;DR

This paper introduces a code-based cryptographic scheme for federated learning that enhances privacy and efficiency, especially against slow devices, achieving significant speed-ups while maintaining high accuracy.

Contribution

It presents a novel privacy-preserving federated learning scheme using code-based cryptography that is resilient to straggling devices and improves computational privacy.

Findings

Achieves 4.7x and 4x speed-up for 92 and 128 bits security levels.

Maintains 95% accuracy on MNIST dataset.

Resilient to straggling devices in federated learning.

Abstract

We propose a privacy-preserving federated learning (FL) scheme that is resilient against straggling devices. An adaptive scenario is suggested where the slower devices share their data with the faster ones and do not participate in the learning process. The proposed scheme employs code-based cryptography to ensure \emph{computational} privacy of the private data, i.e., no device with bounded computational power can obtain information about the other devices' data in feasible time. For a scenario with 25 devices, the proposed scheme achieves a speed-up of 4.7 and 4 for 92 and 128 bits security, respectively, for an accuracy of 95\% on the MNIST dataset compared with conventional mini-batch FL.