# Privacy-Preserving Image Classification Using ConvMixer with Adaptive Permutation Matrix

arXiv: https://arxiv.org/abs/2208.02556 · HTML: https://mlsanity.com/paper/2208.02556/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 4 Aug 2022.

## Builds on (most cited first, 9 of 9)

- [Patches Are All You Need?](https://mlsanity.com/paper/2201.09792/) (2022)
- [Encryption-then-Compression Systems using Grayscale-based Image Encryption for JPEG Images](https://mlsanity.com/paper/1811.00236/) (2018)
- [Learnable Image Encryption](https://mlsanity.com/paper/1804.00490/) (2018)
- [An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applications](https://mlsanity.com/paper/2201.11006/) (2022)
- [Block-wise Scrambled Image Recognition Using Adaptation Network](https://mlsanity.com/paper/2001.07761/) (2020)
- [A GAN-Based Image Transformation Scheme for Privacy-Preserving Deep Neural Networks](https://mlsanity.com/paper/2006.01342/) (2020)
- [Privacy-Preserving Image Classification Using Isotropic Network](https://mlsanity.com/paper/2204.07707/) (2022)
- [Attacks on Image Encryption Schemes for Privacy-Preserving Deep Neural Networks](https://mlsanity.com/paper/2004.13263/) (2020)
- [Image and Model Transformation with Secret Key for Vision Transformer](https://mlsanity.com/paper/2207.05366/) (2022)

## Abstract (arXiv)

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.