mlsanityData to 7 Oct 2026

A GAN-Based Image Transformation Scheme for Privacy-Preserving Deep Neural Networks

arXiv 2006.01342 ↗First posted 2 Jun 2020cs.CR eess.IVcited by 27

Not on the map. Why?

Abstract (arXiv)

We propose a novel image transformation scheme using generative adversarial networks (GANs) for privacy-preserving deep neural networks (DNNs). The proposed scheme enables us not only to apply images without visual information to DNNs, but also to enhance robustness against ciphertext-only attacks (COAs) including DNN-based attacks. In this paper, the proposed transformation scheme is demonstrated to be able to protect visual information on plain images, and the visually-protected images are directly applied to DNNs for privacy-preserving image classification. Since the proposed scheme utilizes GANs, there is no need to manage encryption keys. In an image classification experiment, we evaluate the effectiveness of the proposed scheme in terms of classification accuracy and robustness against COAs.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 11; 2023: 4; 2024: 4; 2025: 1.

27 papers.

Sort:

  1. 2023Re-thinking Model Inversion Attacks Against Deep Neural Networkscited by 39
  2. 2022An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applicationscited by 29
  3. 2023Diff-Privacy: Diffusion-based Face Privacy Protectioncited by 25
  4. 2021A Protection Method of Trained CNN Model with Secret Key from Unauthorized Accesscited by 15
  5. 2022Image and Model Transformation with Secret Key for Vision Transformercited by 12
  6. 2021Piracy-Resistant DNN Watermarking by Block-Wise Image Transformation with Secret Keycited by 9
  7. 2022Privacy-Preserving Image Classification Using Vision Transformercited by 9
  8. 2022Hiding Visual Information via Obfuscating Adversarial Perturbationscited by 7
  9. 2021Access Control Using Spatially Invariant Permutation of Feature Maps for Semantic Segmentation Modelscited by 4
  10. 2021Leveraging Image-based Generative Adversarial Networks for Time Series Generationcited by 4
  11. 2022On the Transferability of Adversarial Examples between Encrypted Modelscited by 4
  12. 2022Access Control of Semantic Segmentation Models Using Encrypted Feature Mapscited by 3
15 more
  1. 2023Color-NeuraCrypt: Privacy-Preserving Color-Image Classification Using Extended Random Neural Networkscited by 2
  2. 2024Unveiling Hidden Visual Information: A Reconstruction Attack Against Adversarial Visual Information Hidingcited by 2
  3. 2021Transfer Learning-Based Model Protection With Secret Keycited by 1
  4. 2022StyleGAN Encoder-Based Attack for Block Scrambled Face Imagescited by 1
  5. 2022Access Control with Encrypted Feature Maps for Object Detection Modelscited by 1
  6. 2024Ensembler: Protect Collaborative Inference Privacy from Model Inversion Attack via Selective Ensemblecited by 1
  7. 2024Privacy-Preserving Deep Learning Using Deformable Operators for Secure Task Learningcited by 1
  8. 2021A Lightweight Privacy-Preserving Scheme Using Label-based Pixel Block Mixing for Image Classification in Deep Learningcited by 0
  9. 2021Protecting Semantic Segmentation Models by Using Block-wise Image Encryption with Secret Key from Unauthorized Accesscited by 0
  10. 2022An Encryption Method of ConvMixer Models without Performance Degradationcited by 0
  11. 2022Privacy-Preserving Image Classification Using ConvMixer with Adaptive Permutation Matrixcited by 0
  12. 2022On the Adversarial Transferability of ConvMixer Modelscited by 0
  13. 2023A Privacy Preserving Method with a Random Orthogonal Matrix for ConvMixer Modelscited by 0
  14. 2024Attack GAN (AGAN ): A new Security Evaluation Tool for Perceptual Encryptioncited by 0
  15. 2025Generative Adversarial Networks Applied for Privacy Preservation in Biometric-Based Authentication and Identificationcited by 0