Privacy-Preserving Vision Transformer Using Images Encrypted with Restricted Random Permutation Matrices
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 9 of its 12 references that are in the map. First posted on arXiv 16 Aug 2024.
Builds on
9 of 12 references.
References · 9
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2022An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applicationscited by 29
- 2020Block-wise Scrambled Image Recognition Using Adaptation Networkcited by 27
- 2022Privacy-Preserving Image Classification Using Isotropic Networkcited by 17
- 2022Image and Model Transformation with Secret Key for Vision Transformercited by 12
- 2022Multi-Task Distributed Learning using Vision Transformer with Random Patch Permutationcited by 10
- 2018Grayscale-based Block Scrambling Image Encryption for Social Networking Servicescited by 6
- 2024Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformercited by 3
- 2024A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defensecited by 3
Built on by
Not cited yet.