Just a Simple Transformation is Enough for Data Protection in Vertical Federated Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Semenov, Andrei, Zmushko, Philip, Pichugin, Alexander, Beznosikov, Aleksandr
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909430541451264
author Semenov, Andrei
Zmushko, Philip
Pichugin, Alexander
Beznosikov, Aleksandr
author_facet Semenov, Andrei
Zmushko, Philip
Pichugin, Alexander
Beznosikov, Aleksandr
contents Vertical Federated Learning (VFL) aims to enable collaborative training of deep learning models while maintaining privacy protection. However, the VFL procedure still has components that are vulnerable to attacks by malicious parties. In our work, we consider feature reconstruction attacks, a common risk targeting input data compromise. We theoretically claim that feature reconstruction attacks cannot succeed without knowledge of the prior distribution on data. Consequently, we demonstrate that even simple model architecture transformations can significantly impact the protection of input data during VFL. Confirming these findings with experimental results, we show that MLP-based models are resistant to state-of-the-art feature reconstruction attacks.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11689
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Just a Simple Transformation is Enough for Data Protection in Vertical Federated Learning
Semenov, Andrei
Zmushko, Philip
Pichugin, Alexander
Beznosikov, Aleksandr
Machine Learning
Cryptography and Security
I.2.m; F.2.0
Vertical Federated Learning (VFL) aims to enable collaborative training of deep learning models while maintaining privacy protection. However, the VFL procedure still has components that are vulnerable to attacks by malicious parties. In our work, we consider feature reconstruction attacks, a common risk targeting input data compromise. We theoretically claim that feature reconstruction attacks cannot succeed without knowledge of the prior distribution on data. Consequently, we demonstrate that even simple model architecture transformations can significantly impact the protection of input data during VFL. Confirming these findings with experimental results, we show that MLP-based models are resistant to state-of-the-art feature reconstruction attacks.
title Just a Simple Transformation is Enough for Data Protection in Vertical Federated Learning
topic Machine Learning
Cryptography and Security
I.2.m; F.2.0
url https://arxiv.org/abs/2412.11689