Secure Vertical Federated Learning Under Unreliable Connectivity
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| 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 |