mlsanityData to 14 Oct 2026

Privacy-Preserving Image Classification Using Vision Transformer

arXiv 2205.12041 ↗First posted 24 May 2022cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a privacy-preserving image classification method that is based on the combined use of encrypted images and the vision transformer (ViT). The proposed method allows us not only to apply images without visual information to ViT models for both training and testing but to also maintain a high classification accuracy. ViT utilizes patch embedding and position embedding for image patches, so this architecture is shown to reduce the influence of block-wise image transformation. In an experiment, the proposed method for privacy-preserving image classification is demonstrated to outperform state-of-the-art methods in terms of classification accuracy and robustness against various attacks.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 14 of its 32 references that are in the map. First posted on arXiv 24 May 2022.

Builds on

14 of 32 references.

References · 14

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  6. 2018ShakeDrop Regularization for Deep Residual Learningcited by 40
  7. 2018Encryption-then-Compression Systems using Grayscale-based Image Encryption for JPEG Imagescited by 34
  8. 2018Learnable Image Encryptioncited by 33
  9. 2022An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applicationscited by 29
  10. 2020Block-wise Scrambled Image Recognition Using Adaptation Networkcited by 27
  11. 2020A GAN-Based Image Transformation Scheme for Privacy-Preserving Deep Neural Networkscited by 27
  12. 2022Privacy-Preserving Image Classification Using Isotropic Networkcited by 17
2 more
  1. 2020Attacks on Image Encryption Schemes for Privacy-Preserving Deep Neural Networkscited by 12
  2. 2020Image Transformation Network for Privacy-Preserving Deep Neural Networks and Its Security Evaluationcited by 8

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 4; 2024: 4.

9 papers.

  1. 2022Image and Model Transformation with Secret Key for Vision Transformercited by 12
  2. 2023Generative Model-Based Attack on Learnable Image Encryption for Privacy-Preserving Deep Learningcited by 4
  3. 2024Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformercited by 3
  4. 2024A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defensecited by 3
  5. 2023Color-NeuraCrypt: Privacy-Preserving Color-Image Classification Using Extended Random Neural Networkscited by 2
  6. 2024Preserving Data Privacy for ML-driven Applications in Open Radio Access Networkscited by 2
  7. 2023Domain Adaptation for Efficiently Fine-tuning Vision Transformer with Encrypted Imagescited by 1
  8. 2024Privacy-Preserving Deep Learning Using Deformable Operators for Secure Task Learningcited by 1
  9. 2023A Privacy Preserving Method with a Random Orthogonal Matrix for ConvMixer Modelscited by 0