English

An Encryption Method of ConvMixer Models without Performance Degradation

Cryptography and Security 2022-07-26 v1 Computer Vision and Pattern Recognition

Abstract

In this paper, we propose an encryption method for ConvMixer models with a secret key. Encryption methods for DNN models have been studied to achieve adversarial defense, model protection and privacy-preserving image classification. However, the use of conventional encryption methods degrades the performance of models compared with that of plain models. Accordingly, we propose a novel method for encrypting ConvMixer models. The method is carried out on the basis of an embedding architecture that ConvMixer has, and models encrypted with the method can have the same performance as models trained with plain images only when using test images encrypted with a secret key. In addition, the proposed method does not require any specially prepared data for model training or network modification. In an experiment, the effectiveness of the proposed method is evaluated in terms of classification accuracy and model protection in an image classification task on the CIFAR10 dataset.

Keywords

Cite

@article{arxiv.2207.11939,
  title  = {An Encryption Method of ConvMixer Models without Performance Degradation},
  author = {Ryota Iijima and Hitoshi Kiya},
  journal= {arXiv preprint arXiv:2207.11939},
  year   = {2022}
}

Comments

6 pages, 5 figures. arXiv admin note: substantial text overlap with arXiv:2207.05366

R2 v1 2026-06-25T01:11:31.354Z