Block-wise Scrambled Image Recognition Using Adaptation Network

TL;DR

This paper introduces a method combining block-wise image scrambling and an adaptation network to enable recognition of perceptually hidden images, enhancing security while maintaining classification accuracy.

Contribution

It proposes a novel adaptation network capable of recognizing scrambled images, advancing secure image recognition techniques.

Findings

The adaptation network effectively recognizes scrambled images.

Block-wise scrambling successfully hides perceptual information.

The method performs well on CIFAR datasets.

Abstract

In this study, a perceptually hidden object-recognition method is investigated to generate secure images recognizable by humans but not machines. Hence, both the perceptual information hiding and the corresponding object recognition methods should be developed. Block-wise image scrambling is introduced to hide perceptual information from a third party. In addition, an adaptation network is proposed to recognize those scrambled images. Experimental comparisons conducted using CIFAR datasets demonstrated that the proposed adaptation network performed well in incorporating simple perceptual information hiding into DNN-based image classification.