Secure Vertical Federated Learning Under Unreliable Connectivity

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qiu, Xinchi, Pan, Heng, Zhao, Wanru, Gao, Yan, Gusmao, Pedro P. B., Shen, William F., Ma, Chenyang, Lane, Nicholas D.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929246181523456
author Qiu, Xinchi
Pan, Heng
Zhao, Wanru
Gao, Yan
Gusmao, Pedro P. B.
Shen, William F.
Ma, Chenyang
Lane, Nicholas D.
author_facet Qiu, Xinchi
Pan, Heng
Zhao, Wanru
Gao, Yan
Gusmao, Pedro P. B.
Shen, William F.
Ma, Chenyang
Lane, Nicholas D.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2305_16794
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Secure Vertical Federated Learning Under Unreliable Connectivity
Qiu, Xinchi
Pan, Heng
Zhao, Wanru
Gao, Yan
Gusmao, Pedro P. B.
Shen, William F.
Ma, Chenyang
Lane, Nicholas D.
Cryptography and Security
Machine Learning
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.
title Secure Vertical Federated Learning Under Unreliable Connectivity
topic Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2305.16794