mlsanityData to 7 Oct 2026

Image and Model Transformation with Secret Key for Vision Transformer

arXiv 2207.05366 ↗First posted 12 Jul 2022cs.CV cs.CRcited by 12

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a combined use of transformed images and vision transformer (ViT) models transformed with a secret key. We show for the first time that models trained with plain images can be directly transformed to models trained with encrypted images on the basis of the ViT architecture, and the performance of the transformed models is the same as models trained with plain images when using test images encrypted with the key. In addition, the proposed scheme does not require any specially prepared data for training models or network modification, so it also allows us to easily update the secret key. In an experiment, the effectiveness of the proposed scheme is evaluated in terms of performance degradation and model protection performance in an image classification task on the CIFAR-10 dataset.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 30 of its 61 references that are in the map. First posted on arXiv 12 Jul 2022.

Builds on

30 of 61 references.

References · 30

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  5. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  6. 2021Pay Attention to MLPscited by 367
  7. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 338
  8. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
  9. 2017Embedding Watermarks into Deep Neural Networkscited by 227
  10. 2022Patches Are All You Need?cited by 201
  11. 2021CycleMLP: A MLP-like Architecture for Dense Predictioncited by 126
  12. 2020Adversarial Machine Learning -- Industry Perspectivescited by 121
18 more
  1. 2017Adversarial Frontier Stitching for Remote Neural Network Watermarkingcited by 110
  2. 2021Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognitioncited by 103
  3. 2018Recent progress in semantic image segmentationcited by 39
  4. 2018Learnable Image Encryptioncited by 33
  5. 2018Encryption-then-Compression Systems using Grayscale-based Image Encryption for JPEG Imagescited by 33
  6. 2020Block-wise Image Transformation with Secret Key for Adversarially Robust Defensecited by 30
  7. 2022An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applicationscited by 29
  8. 2020A GAN-Based Image Transformation Scheme for Privacy-Preserving Deep Neural Networkscited by 27
  9. 2019Privacy-Preserving Deep Neural Networks with Pixel-based Image Encryption Considering Data Augmentation in the Encrypted Domaincited by 19
  10. 2020Encryption Inspired Adversarial Defense for Visual Classificationcited by 17
  11. 2022Privacy-Preserving Image Classification Using Isotropic Networkcited by 17
  12. 2021A Protection Method of Trained CNN Model with Secret Key from Unauthorized Accesscited by 15
  13. 2020A Privacy-Preserving Machine Learning Scheme Using EtC Imagescited by 9
  14. 2022Privacy-Preserving Image Classification Using Vision Transformercited by 9
  15. 2013P3: Toward Privacy-Preserving Photo Sharingcited by 8
  16. 2019Privacy-Preserving Support Vector Machine Computing Using Random Unitary Transformationcited by 5
  17. 2022Block shuffling learning for Deepfake Detectioncited by 4
  18. 2020A Reversible Data Hiding Method in Compressible Encrypted Imagescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 3; 2025: 2; 2026: 1.

12 papers.

  1. 2024Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformercited by 3
  2. 2023Color-NeuraCrypt: Privacy-Preserving Color-Image Classification Using Extended Random Neural Networkscited by 2
  3. 2023Domain Adaptation for Efficiently Fine-tuning Vision Transformer with Encrypted Imagescited by 1
  4. 2025A Privacy-Preserving Semantic-Segmentation Method Using Domain-Adaptation Techniquecited by 1
  5. 2025Keys in the Weights: Transformer Authentication Using Model-Bound Latent Representationscited by 1
  6. 2022Privacy-Preserving Image Classification Using ConvMixer with Adaptive Permutation Matrixcited by 0
  7. 2022An Access Control Method with Secret Key for Semantic Segmentation Modelscited by 0
  8. 2023A Privacy Preserving Method with a Random Orthogonal Matrix for ConvMixer Modelscited by 0
  9. 2023Combined Use of Federated Learning and Image Encryption for Privacy-Preserving Image Classification with Vision Transformercited by 0
  10. 2024XNN: Paradigm Shift in Mitigating Identity Leakage within Cloud-Enabled Deep Learningcited by 0
  11. 2024Privacy-Preserving Vision Transformer Using Images Encrypted with Restricted Random Permutation Matricescited by 0
  12. 2026Privacy-Preserving Clothing Classification using Vision Transformer for Thermal Comfort Estimationcited by 0