Block-wise Scrambled Image Recognition Using Adaptation Network

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.

6 pages Artificial Intelligence of Things(AAAI-2020 WS)

References in corpus (2)

• ShakeDrop Regularization for Deep Residual Learning
• AutoShuffleNet: Learning Permutation Matrices via an Exact Lipschitz Continuous Penalty in Deep Convolutional Neural Networks

Cited by in corpus (5)

• Attacks on Image Encryption Schemes for Privacy-Preserving Deep Neural Networks
• Access Control Using Spatially Invariant Permutation of Feature Maps for Semantic Segmentation Models
• Privacy-Preserving Deep Learning Using Deformable Operators for Secure Task Learning
• Access Control with Encrypted Feature Maps for Object Detection Models
• Multitask Identity-Aware Image Steganography via Minimax Optimization