Privacy-Preserving Image Classification Using ConvMixer with Adaptive Permutation Matrix
This addresses privacy concerns in image classification for applications like surveillance or medical imaging, though it is incremental as it builds on existing ConvMixer and encryption techniques.
The paper tackles the problem of privacy-preserving image classification with encrypted images by proposing a method using ConvMixer and adaptive permutation matrices, eliminating the need for an adaptation network and achieving higher classification accuracy than conventional methods.
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.