AI Chat AI Image Generator AI Video Text to Speech

Block Scrambling Image Encryption Used in Combination with Data Augmentation for Privacy-Preserving DNNs

04/03/2021

∙

by Tatsuya Chuman, et al.

∙

∙

In this paper, we propose a novel learnable image encryption method for privacy-preserving deep neural networks (DNNs). The proposed method is carried out on the basis of block scrambling used in combination with data augmentation techniques such as random cropping, horizontal flip and grid mask. The use of block scrambling enhances robustness against various attacks, and in contrast, the combination with data augmentation enables us to maintain a high classification accuracy even when using encrypted images. In an image classification experiment, the proposed method is demonstrated to be effective in privacy-preserving DNNs.

Tatsuya Chuman
12 publications
Hitoshi Kiya
97 publications

research

∙ 05/06/2019

Privacy-Preserving Deep Neural Networks with Pixel-based Image Encryption Considering Data Augmentation in the Encrypted Domain

We present a novel privacy-preserving scheme for deep neural networks (D...

0 Warit Sirichotedumrong, et al. ∙

research

∙ 04/16/2022

Privacy-Preserving Image Classification Using Isotropic Network

In this paper, we propose a privacy-preserving image classification meth...

0 AprilPyone MaungMaung, et al. ∙

research

∙ 05/19/2021

A Lightweight Privacy-Preserving Scheme Using Label-based Pixel Block Mixing for Image Classification in Deep Learning

To ensure the privacy of sensitive data used in the training of deep lea...

0 Yuexin Xiang, et al. ∙

research

∙ 06/02/2020

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

We propose a novel image transformation scheme using generative adversar...

0 Warit Sirichotedumrong, et al. ∙

research

∙ 08/07/2020

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

We propose a transformation network for generating visually-protected im...

0 Hiroki Ito, et al. ∙

research

∙ 08/10/2023

A Homomorphic Encryption Framework for Privacy-Preserving Spiking Neural Networks

Machine learning (ML) is widely used today, especially through deep neur...

0 Farzad Nikfam, et al. ∙

research

∙ 04/07/2017

Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption

We propose a privacy-preserving framework for learning visual classifier...

0 Ryo Yonetani, et al. ∙