Attacks on Image Encryption Schemes for Privacy-Preserving Deep Neural Networks
Not on the map. Why?
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.
Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Apr 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 6; 2023: 2; 2024: 3.
12 papers.
- 2022An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applicationscited by 29
- 2022Privacy-Preserving Image Classification Using Isotropic Networkcited by 17
- 2022Privacy-Preserving Image Classification Using Vision Transformercited by 9
- 2023Generative Model-Based Attack on Learnable Image Encryption for Privacy-Preserving Deep Learningcited by 4
- 2024Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformercited by 3
- 2022StyleGAN Encoder-Based Attack for Block Scrambled Face Imagescited by 1
- 2023Domain Adaptation for Efficiently Fine-tuning Vision Transformer with Encrypted Imagescited by 1
- 2021A Privacy-Preserving Image Retrieval Scheme Using A Codebook Generated From Independent Plain-Image Datasetcited by 0
- 2022A Pixel-based Encryption Method for Privacy-Preserving Deep Learning Modelscited by 0
- 2022Privacy-Preserving Image Classification Using ConvMixer with Adaptive Permutation Matrixcited by 0
- 2024Privacy-Preserving and Trustworthy Deep Learning for Medical Imagingcited by 0
- 2024Attack GAN (AGAN ): A new Security Evaluation Tool for Perceptual Encryptioncited by 0
- 2024Attack GAN (AGAN ): A new Security Evaluation Tool for Perceptual Encryption9 Jul 2024
- 2024Privacy-Preserving and Trustworthy Deep Learning for Medical Imaging29 Jun 2024
- 2024Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformer10 Jan 2024
- 2023Domain Adaptation for Efficiently Fine-tuning Vision Transformer with Encrypted Images5 Sep 2023
- 2023Generative Model-Based Attack on Learnable Image Encryption for Privacy-Preserving Deep Learning9 Mar 2023
- 2022StyleGAN Encoder-Based Attack for Block Scrambled Face Images16 Sep 2022
- 2022Privacy-Preserving Image Classification Using ConvMixer with Adaptive Permutation Matrix4 Aug 2022
- 2022Privacy-Preserving Image Classification Using Vision Transformer24 May 2022
- 2022Privacy-Preserving Image Classification Using Isotropic Network16 Apr 2022
- 2022A Pixel-based Encryption Method for Privacy-Preserving Deep Learning Models31 Mar 2022
- 2022An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applications26 Jan 2022
- 2021A Privacy-Preserving Image Retrieval Scheme Using A Codebook Generated From Independent Plain-Image Dataset4 Sep 2021