# Block-Wise Encryption for Reliable Vision Transformer models

arXiv: https://arxiv.org/abs/2308.07612 · HTML: https://mlsanity.com/paper/2308.07612/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Aug 2023.

## Built on by (most cited first, 3 of 3)

- [Seed-Induced Uniqueness in Transformer Models: Subspace Alignment Governs Subliminal Transfer](https://mlsanity.com/paper/2511.01023/) (2025)
- [AI-Driven Secure Data Sharing: A Trustworthy and Privacy-Preserving Approach](https://mlsanity.com/paper/2501.15363/) (2025)
- [Keys in the Weights: Transformer Authentication Using Model-Bound Latent Representations](https://mlsanity.com/paper/2511.00973/) (2025)

## Abstract (arXiv)

This article presents block-wise image encryption for the vision transformer and its applications. Perceptual image encryption for deep learning enables us not only to protect the visual information of plain images but to also embed unique features controlled with a key into images and models. However, when using conventional perceptual encryption methods, the performance of models is degraded due to the influence of encryption. In this paper, we focus on block-wise encryption for the vision transformer, and we introduce three applications: privacy-preserving image classification, access control, and the combined use of federated learning and encrypted images. Our scheme can have the same performance as models without any encryption, and it does not require any network modification. It also allows us to easily update the secret key. In experiments, the effectiveness of the scheme is demonstrated in terms of performance degradation and access control on the CIFAR10 and CIFAR-100 datasets.