Edge-assisted U-Shaped Split Federated Learning with Privacy-preserving for Internet of Things

TL;DR

This paper introduces EUSFL, a privacy-preserving, edge-assisted split federated learning framework for IoT that reduces training time and enhances data security using U-shaped splitting and a novel noise mechanism.

Contribution

The paper proposes a novel U-shaped split federated learning framework with a new LabelDP noise mechanism, improving training efficiency and privacy protection for IoT devices.

Findings

EUSFL significantly reduces training time and local computation overhead.

The framework maintains good performance across diverse IoT device capabilities.

The LabelDP mechanism effectively resists reconstruction attacks.

Abstract

In the realm of the Internet of Things (IoT), deploying deep learning models to process data generated or collected by IoT devices is a critical challenge. However, direct data transmission can cause network congestion and inefficient execution, given that IoT devices typically lack computation and communication capabilities. Centralized data processing in data centers is also no longer feasible due to concerns over data privacy and security. To address these challenges, we present an innovative Edge-assisted U-Shaped Split Federated Learning (EUSFL) framework, which harnesses the high-performance capabilities of edge servers to assist IoT devices in model training and optimization process. In this framework, we leverage Federated Learning (FL) to enable data holders to collaboratively train models without sharing their data, thereby enhancing data privacy protection by transmitting only model parameters. Additionally, inspired by Split Learning (SL), we split the neural network into three parts using U-shaped splitting for local training on IoT devices. By exploiting the greater computation capability of edge servers, our framework effectively reduces overall training time and allows IoT devices with varying capabilities to perform training tasks efficiently. Furthermore, we proposed a novel noise mechanism called LabelDP to ensure that data features and labels can securely resist reconstruction attacks, eliminating the risk of privacy leakage. Our theoretical analysis and experimental results demonstrate that EUSFL can be integrated with various aggregation algorithms, maintaining good performance across different computing capabilities of IoT devices, and significantly reducing training time and local computation overhead.