Efficient Privacy-Preserving Federated Learning With Improved Compressed Sensing

Publication Type

Journal Article

Publication Date

8-2023

Abstract

To solve the data silos issue in distributed machine learning with privacy leakage, privacy-preserving federated learning (PPFL) has been extensively explored in both academic and industrial fields. However, the existing PPFL solutions still suffer from high computation and communication overheads, which result in excessive consumption of communication bandwidth and slow down the training process of FL. To address these issues, we propose a secure and communication-efficient FL scheme using improved compressed sensing and CKKS homomorphic encryption. Specifically, we implement a lossy compression of the model by using discrete cosine transform, then use CKKS homomorphic encryption to encrypt the data transmitted between clients and center server due to its high efficiency and support for batch encryption. Formal security analysis proves that our scheme is secure against indistinguishability under chosen plaintext attack and extensive experiments demonstrate that our scheme achieves a high accuracy at 0.05% compression rate.

Keywords

CKKS, communication costs, compression sensing (CS), federated learning (FL), homomorphic encryption

Discipline

Artificial Intelligence and Robotics

Research Areas

Cybersecurity

Publication

IEEE Transactions on Industrial Informatics

ISSN

1551-3203

Identifier

10.1109/TII.2023.3297596

Publisher

Institute of Electrical and Electronics Engineers

Additional URL

https://doi.org/10.1109/TII.2023.3297596

This document is currently not available here.

Share

COinS