Privacy-Preserving Image Classification Using ConvMixer with Adaptive Permutation Matrix

TL;DR

This paper introduces a privacy-preserving image classification method using ConvMixer and adaptive permutation matrices, enabling effective classification of encrypted images without additional adaptation networks, and achieving higher accuracy.

Contribution

It proposes a novel approach that allows ConvMixer to classify encrypted images directly, eliminating the need for adaptation networks and improving accuracy over existing methods.

Findings

Effective classification of encrypted images with ConvMixer.

Higher accuracy compared to conventional privacy-preserving methods.

Elimination of adaptation network requirement.

Abstract

In this paper, we propose a privacy-preserving image classification method using encrypted images under the use of the ConvMixer structure. Block-wise scrambled images, which are robust enough against various attacks, have been used for privacy-preserving image classification tasks, but the combined use of a classification network and an adaptation network is needed to reduce the influence of image encryption. However, images with a large size cannot be applied to the conventional method with an adaptation network because the adaptation network has so many parameters. Accordingly, we propose a novel method, which allows us not only to apply block-wise scrambled images to ConvMixer for both training and testing without the adaptation network, but also to provide a higher classification accuracy than conventional methods.