Privacy-Preserving Vision Transformer Using Images Encrypted with Restricted Random Permutation Matrices

Kouki Horio, Kiyoshi Nishikawa, Hitoshi Kiya
8/16/2024
cs.CV

No confident code implementation found for this paper. 2 possible matches can be shown below.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 2 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

I can't see it but I can Fine-tune it: On Encrypted Fine-tuning of Transformers using Fully Homomorphic Encryption

86% match2024

Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformer

83% match2024

Effective Fine-Tuning of Vision Transformers with Low-Rank Adaptation for Privacy-Preserving Image Classification

83% match2025

Human-imperceptible, Machine-recognizable Images

82% match1 repo52023

Encryption-Friendly LLM Architecture

81% match2026

A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defense

81% match2024

Cite this paper

@article{horio2024privacypreserving,
  title  = {Privacy-Preserving Vision Transformer Using Images Encrypted with Restricted Random Permutation Matrices},
  author = {Kouki Horio and Kiyoshi Nishikawa and Hitoshi Kiya},
  year   = {2024},
  eprint = {2408.08529},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2408.08529v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2408.08529.svg)](https://codeofpaper.com/paper/2408.08529)

Discussion