Disposable-key-based image encryption for collaborative learning of Vision Transformer

TL;DR

This paper introduces a secure image encryption method for federated learning of Vision Transformers, enabling clients to encrypt images with disposable keys, reducing communication costs, and maintaining classification accuracy.

Contribution

It presents a novel encryption approach allowing clients to dispose of keys and train ViT models on encrypted images, enhancing privacy and efficiency in collaborative learning.

Findings

Effective classification accuracy on CIFAR-10

Reduced communication costs with disposable keys

Secure training on encrypted images

Abstract

We propose a novel method for securely training the vision transformer (ViT) with sensitive data shared from multiple clients similar to privacy-preserving federated learning. In the proposed method, training images are independently encrypted by each client where encryption keys can be prepared by each client, and ViT is trained by using these encrypted images for the first time. The method allows clients not only to dispose of the keys but to also reduce the communication costs between a central server and the clients. In image classification experiments, we verify the effectiveness of the proposed method on the CIFAR-10 dataset in terms of classification accuracy and the use of restricted random permutation matrices.