# Attacks on Image Encryption Schemes for Privacy-Preserving Deep Neural Networks

arXiv: https://arxiv.org/abs/2004.13263 · HTML: https://mlsanity.com/paper/2004.13263/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Apr 2020.

## Built on by (most cited first, 12 of 12)

- [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)
- [Privacy-Preserving Image Classification Using Vision Transformer](https://mlsanity.com/paper/2205.12041/) (2022)
- [Generative Model-Based Attack on Learnable Image Encryption for Privacy-Preserving Deep Learning](https://mlsanity.com/paper/2303.05036/) (2023)
- [Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformer](https://mlsanity.com/paper/2401.05126/) (2024)
- [StyleGAN Encoder-Based Attack for Block Scrambled Face Images](https://mlsanity.com/paper/2209.07953/) (2022)
- [Domain Adaptation for Efficiently Fine-tuning Vision Transformer with Encrypted Images](https://mlsanity.com/paper/2309.02556/) (2023)
- [A Privacy-Preserving Image Retrieval Scheme Using A Codebook Generated From Independent Plain-Image Dataset](https://mlsanity.com/paper/2109.01841/) (2021)
- [A Pixel-based Encryption Method for Privacy-Preserving Deep Learning Models](https://mlsanity.com/paper/2203.16780/) (2022)
- [Privacy-Preserving Image Classification Using ConvMixer with Adaptive Permutation Matrix](https://mlsanity.com/paper/2208.02556/) (2022)
- [Privacy-Preserving and Trustworthy Deep Learning for Medical Imaging](https://mlsanity.com/paper/2407.00538/) (2024)
- [Attack GAN (AGAN ): A new Security Evaluation Tool for Perceptual Encryption](https://mlsanity.com/paper/2407.06570/) (2024)

## Abstract (arXiv)

Privacy preserving machine learning is an active area of research usually relying on techniques such as homomorphic encryption or secure multiparty computation. Recent novel encryption techniques for performing machine learning using deep neural nets on images have recently been proposed by Tanaka and Sirichotedumrong, Kinoshita, and Kiya. We present new chosen-plaintext and ciphertext-only attacks against both of these proposed image encryption schemes and demonstrate the attacks' effectiveness on several examples.