Saved in:
Bibliographic Details
Main Authors: Horio, Kouki, Nishikawa, Kiyoshi, Kiya, Hitoshi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.08529
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910567884652544
author Horio, Kouki
Nishikawa, Kiyoshi
Kiya, Hitoshi
author_facet Horio, Kouki
Nishikawa, Kiyoshi
Kiya, Hitoshi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_08529
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Privacy-Preserving Vision Transformer Using Images Encrypted with Restricted Random Permutation Matrices
Horio, Kouki
Nishikawa, Kiyoshi
Kiya, Hitoshi
Computer Vision and Pattern Recognition
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.
title Privacy-Preserving Vision Transformer Using Images Encrypted with Restricted Random Permutation Matrices
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.08529