# Image Transformation Network for Privacy-Preserving Deep Neural Networks and Its Security Evaluation

arXiv: https://arxiv.org/abs/2008.03143 · HTML: https://mlsanity.com/paper/2008.03143/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2020.

## Built on by (most cited first, 8 of 8)

- [An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applications](https://mlsanity.com/paper/2201.11006/) (2022)
- [A Protection Method of Trained CNN Model with Secret Key from Unauthorized Access](https://mlsanity.com/paper/2105.14756/) (2021)
- [Piracy-Resistant DNN Watermarking by Block-Wise Image Transformation with Secret Key](https://mlsanity.com/paper/2104.04241/) (2021)
- [Privacy-Preserving Image Classification Using Vision Transformer](https://mlsanity.com/paper/2205.12041/) (2022)
- [Hiding Visual Information via Obfuscating Adversarial Perturbations](https://mlsanity.com/paper/2209.15304/) (2022)
- [Transfer Learning-Based Model Protection With Secret Key](https://mlsanity.com/paper/2103.03525/) (2021)
- [Attack GAN (AGAN ): A new Security Evaluation Tool for Perceptual Encryption](https://mlsanity.com/paper/2407.06570/) (2024)
- [Generative Adversarial Networks Applied for Privacy Preservation in Biometric-Based Authentication and Identification](https://mlsanity.com/paper/2509.20024/) (2025)

## Abstract (arXiv)

We propose a transformation network for generating visually-protected images for privacy-preserving DNNs. The proposed transformation network is trained by using a plain image dataset so that plain images are transformed into visually protected ones. Conventional perceptual encryption methods have a weak visual-protection performance and some accuracy degradation in image classification. In contrast, the proposed network enables us not only to strongly protect visual information but also to maintain the image classification accuracy that using plain images achieves. In an image classification experiment, the proposed network is demonstrated to strongly protect visual information on plain images without any performance degradation under the use of CIFAR datasets. In addition, it is shown that the visually protected images are robust against a DNN-based attack, called inverse transformation network attack (ITN-Attack) in an experiment.