Exploring the Privacy-Energy Consumption Tradeoff for Split Federated Learning

TL;DR

This paper analyzes how the choice of cut layer in Split Federated Learning impacts client privacy and energy consumption, offering strategies to optimize these trade-offs and discussing future research directions.

Contribution

It provides a comprehensive analysis of energy and privacy trade-offs in SFL, including a method for selecting cut layers to balance privacy risks and energy use.

Findings

Optimal cut layer selection can reduce privacy risks.

Energy consumption is significantly affected by the choice of cut layer.

Trade-offs exist between privacy preservation and energy efficiency.

Abstract

Split Federated Learning (SFL) has recently emerged as a promising distributed learning technology, leveraging the strengths of both federated and split learning. It emphasizes the advantages of rapid convergence while addressing privacy concerns. As a result, this innovation has received significant attention from both industry and academia. However, since the model is split at a specific layer, known as a cut layer, into both client-side and server-side models for the SFL, the choice of the cut layer in SFL can have a substantial impact on the energy consumption of clients and their privacy, as it influences the training burden and the output of the client-side models. In this article, we provide a comprehensive overview of the SFL process and thoroughly analyze energy consumption and privacy. This analysis considers the influence of various system parameters on the cut layer selection strategy. Additionally, we provide an illustrative example of the cut layer selection, aiming to minimize clients' risk of reconstructing the raw data at the server while sustaining energy consumption within the required energy budget, which involves trade-offs. Finally, we address open challenges in this field. These directions represent promising avenues for future research and development.