# Combined Use of Federated Learning and Image Encryption for Privacy-Preserving Image Classification with Vision Transformer

arXiv: https://arxiv.org/abs/2301.09255 · HTML: https://mlsanity.com/paper/2301.09255/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 12 references that are in the map.
- First posted on arXiv 23 Jan 2023.

## Builds on (most cited first, 8 of 8)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applications](https://mlsanity.com/paper/2201.11006/) (2022)
- [Privacy-Preserving Image Classification Using Isotropic Network](https://mlsanity.com/paper/2204.07707/) (2022)
- [Image and Model Transformation with Secret Key for Vision Transformer](https://mlsanity.com/paper/2207.05366/) (2022)
- [Grayscale-based Block Scrambling Image Encryption for Social Networking Services](https://mlsanity.com/paper/1806.03787/) (2018)

## Abstract (arXiv)

In recent years, privacy-preserving methods for deep learning have become an urgent problem. Accordingly, we propose the combined use of federated learning (FL) and encrypted images for privacy-preserving image classification under the use of the vision transformer (ViT). The proposed method allows us not only to train models over multiple participants without directly sharing their raw data but to also protect the privacy of test (query) images for the first time. In addition, it can also maintain the same accuracy as normally trained models. In an experiment, the proposed method was demonstrated to well work without any performance degradation on the CIFAR-10 and CIFAR-100 datasets.