ESMFL: Efficient and Secure Models for Federated Learning

TL;DR

This paper introduces ESMFL, a federated learning approach that enhances privacy and security using Intel SGX, while reducing communication costs through model sparsification, maintaining reasonable accuracy across architectures.

Contribution

The paper presents a novel privacy-preserving federated learning method leveraging Intel SGX and model sparsification to improve security and reduce communication overhead.

Findings

Achieves privacy preservation with Intel SGX in federated learning.

Reduces communication costs via model sparsification.

Maintains reasonable accuracy across different model architectures.

Abstract

Nowadays, Deep Neural Networks are widely applied to various domains. However, massive data collection required for deep neural network reveals the potential privacy issues and also consumes large mounts of communication bandwidth. To address these problems, we propose a privacy-preserving method for the federated learning distributed system, operated on Intel Software Guard Extensions, a set of instructions that increase the security of application code and data. Meanwhile, the encrypted models make the transmission overhead larger. Hence, we reduce the commutation cost by sparsification and it can achieve reasonable accuracy with different model architectures.