DeepAI AI Chat
Log In Sign Up

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

by   Hiroki Ito, et al.
Tokyo Metropolitan University

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.


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

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

Visual Security Evaluation of Learnable Image Encryption Methods against Ciphertext-only Attacks

Various visual information protection methods have been proposed for pri...

A Privacy Preserving Method with a Random Orthogonal Matrix for ConvMixer Models

In this paper, a privacy preserving image classification method is propo...

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

In this paper, we propose a novel learnable image encryption method for ...

Block-Wise Encryption for Reliable Vision Transformer models

This article presents block-wise image encryption for the vision transfo...

Generation of Gradient-Preserving Images allowing HOG Feature Extraction

In this paper, we propose a method for generating visually protected ima...

Poster: On the Feasibility of Training Neural Networks with Visibly Watermarked Dataset

As there are increasing needs of sharing data for machine learning, ther...