Secure Vertical Federated Learning Under Unreliable Connectivity

TL;DR

This paper introduces vFedSec, a novel dropout-tolerant vertical federated learning protocol that enhances security and efficiency, significantly reducing computation and communication costs while being robust to client dropouts.

Contribution

The paper presents vFedSec, the first dropout-tolerant VFL protocol supporting generalized frameworks with secure layer and embedding-padding, improving security and efficiency.

Findings

Achieves over 690x speedup compared to homomorphic encryption methods.

Reduces communication costs by more than 9.6 times.

Demonstrates robustness to client dropout in extensive experiments.

Abstract

Most work in privacy-preserving federated learning (FL) has focused on horizontally partitioned datasets where clients hold the same features and train complete client-level models independently. However, individual data points are often scattered across different institutions, known as clients, in vertical FL (VFL) settings. Addressing this category of FL necessitates the exchange of intermediate outputs and gradients among participants, resulting in potential privacy leakage risks and slow convergence rates. Additionally, in many real-world scenarios, VFL training also faces the acute issue of client stragglers and drop-outs, a serious challenge that can significantly hinder the training process but has been largely overlooked in existing studies. In this work, we present vFedSec, a first dropout-tolerant VFL protocol, which can support the most generalized vertical framework. It achieves secure and efficient model training by using an innovative Secure Layer alongside an embedding-padding technique. We provide theoretical proof that our design attains enhanced security while maintaining training performance. Empirical results from extensive experiments also demonstrate vFedSec is robust to client dropout and provides secure training with negligible computation and communication overhead. Compared to widely adopted homomorphic encryption (HE) methods, our approach achieves a remarkable > 690x speedup and reduces communication costs significantly by > 9.6x.