HidingGAN: High Capacity Information Hiding with Generative Adversarial Network

dc.contributor.authorWang, Zihanen_US
dc.contributor.authorGao, Nengen_US
dc.contributor.authorWang, Xinen_US
dc.contributor.authorXiang, Jien_US
dc.contributor.authorZha, Darenen_US
dc.contributor.authorLi, Linghuien_US
dc.contributor.editorLee, Jehee and Theobalt, Christian and Wetzstein, Gordonen_US
dc.date.accessioned2019-10-14T05:08:25Z
dc.date.available2019-10-14T05:08:25Z
dc.date.issued2019
dc.description.abstractImage steganography is the technique of hiding secret information within images. It is an important research direction in the security field. Benefitting from the rapid development of deep neural networks, many steganographic algorithms based on deep learning have been proposed. However, two problems remain to be solved in which the most existing methods are limited by small image size and information capacity. In this paper, to address these problems, we propose a high capacity image steganographic model named HidingGAN. The proposed model utilizes a new secret information preprocessing method and Inception-ResNet block to promote better integration of secret information and image features. Meanwhile, we introduce generative adversarial networks and perceptual loss to maintain the same statistical characteristics of cover images and stego images in the high-dimensional feature space, thereby improving the undetectability. Through these manners, our model reaches higher imperceptibility, security, and capacity. Experiment results show that our HidingGAN achieves the capacity of 4 bitsper- pixel (bpp) at 256x256 pixels, improving over the previous best result of 0.4 bpp at 32x32 pixels.en_US
dc.description.number7
dc.description.sectionheadersGenerative Models
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume38
dc.identifier.doi10.1111/cgf.13846
dc.identifier.issn1467-8659
dc.identifier.pages393-401
dc.identifier.urihttps://doi.org/10.1111/cgf.13846
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13846
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectSecurity and privacy
dc.subjectPrivacy protections
dc.subjectComputing methodologies
dc.subjectComputer vision tasks
dc.titleHidingGAN: High Capacity Information Hiding with Generative Adversarial Networken_US
Files
Collections