Enhanced Security with Encrypted Vision Transformer in Federated Learning

TL;DR

This paper proposes an encrypted vision transformer framework for federated learning that enhances privacy protection by encrypting model information, demonstrating improved security and accuracy on CIFAR-10.

Contribution

It introduces a novel encrypted vision transformer approach for federated learning, addressing security vulnerabilities against data restoration attacks.

Findings

Improved classification accuracy on CIFAR-10.

Enhanced robustness against model information attacks.

Effective privacy protection through encryption.

Abstract

Federated learning is a learning method for training models over multiple participants without directly sharing their raw data, and it has been expected to be a privacy protection method for training data. In contrast, attack methods have been studied to restore learning data from model information shared with clients, so enhanced security against attacks has become an urgent problem. Accordingly, in this article, we propose a novel framework of federated learning on the bases of the embedded structure of the vision transformer by using the model information encrypted with a random sequence. In image classification experiments, we verify the effectiveness of the proposed method on the CIFAR-10 dataset in terms of classification accuracy and robustness against attacks.