Abstract:
We propose a framework for transformation network training in coordination with a semi-trusted cloud provider for privacy-preserving DNNs. In the framework, a user trains...Show MoreMetadata
Abstract:
We propose a framework for transformation network training in coordination with a semi-trusted cloud provider for privacy-preserving DNNs. In the framework, a user trains a transformation network using a model that a cloud provider has for transforming plain images into visually protected ones. Conventional perceptual encryption methods have a weak visualprotection performance and some accuracy degradation in image classification. In contrast, the proposed framework overcomes the two issues. In an image classification experiment, the transformation network trained under the framework is demonstrated to strongly protect the visual information of plain images, without any performance degradation under the use of two typical classification networks: ResNet and VGG. In addition, it is shown that the visually protected images are robust against a DNN-based attack.
Published in: 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
Date of Conference: 07-10 December 2020
Date Added to IEEE Xplore: 31 December 2020
ISBN Information:
ISSN Information:
Conference Location: Auckland, New Zealand