Encoder-Decoder Architecture for Image Steganography using Skip Connections.

Abstract

Data security has become a basic need in today's world as it shifts more and more toward an all-online mode of operation. All sorts of data and information are now passed from one entity to another over a variety of transmission channels as well as stored on virtual online repositories, and a large chunk of that information is highly private. Over this stream of technological advancements, various data security techniques like encryption, data hiding, etc. have been developed to provide security while transmitting or storing data. This paper proposes an approach to hiding one image inside another image by using CNN in for feature extraction and processing. The proposed model works on the principles of the auto-encoder architecture and is made up of two modules one of which is responsible for the task of processing the secret image and extracting n features and the incorporating those features in the cover image ion such a manner that the cover image retains its original visual qualities and also the secret image gets hidden in it, that module is the Hiding network/Encoder. The other part of this network is the one responsible to then extract the hidden secret image and them create back to its original, this paper is the Reveal network/Decoder. The proposed model is implemented on ImageNet and Pascal-VOC datasets with images of different sizes. In order to judge the models ability to hide the image and to extract is back, PSNR and SSIM are used as performance evaluation Metrics.