# A Privacy Preserving Method with a Random Orthogonal Matrix for ConvMixer Models

Source: [A Privacy Preserving Method with a Random Orthogonal Matrix for ConvMixer Models](<https://www.sota2.com/research/paper/68fa6e631e209131cea3fa0a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:56:59.119Z

Authors: Rei Aso, Tatsuya Chuman, Hitoshi Kiya

Published: 2023-01-10T08:21:19.000Z

## Abstract

In this paper, a privacy preserving image classification method is proposed under the use of ConvMixer models. To protect the visual information of test images, a test image is divided into blocks, and then every block is encrypted by using a random orthogonal matrix. Moreover, a ConvMixer model trained with plain images is transformed by the random orthogonal matrix used for encrypting test images, on the basis of the embedding structure of ConvMixer. The proposed method allows us not only to use the same classification accuracy as that of ConvMixer models without considering privacy protection but to also enhance robustness against various attacks compared to conventional privacy-preserving learning.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2301.03843>)

[PDF](<https://arxiv.org/pdf/2301.03843.pdf>)