We propose a novel method for privacy-preserving fine-tuning vision transformers (ViTs) with encrypted images. Conventional methods using encrypted images degrade model performance compared with that of using plain images due to the influence of image encryption. In contrast, the proposed encryption method using restricted random permutation matrices can provide a higher performance than the conventional ones.
@article{arxiv.2408.08529,
title = {Privacy-Preserving Vision Transformer Using Images Encrypted with Restricted Random Permutation Matrices},
author = {Kouki Horio and Kiyoshi Nishikawa and Hitoshi Kiya},
journal= {arXiv preprint arXiv:2408.08529},
year = {2024}
}