Conditional image hiding network based on style transfer

Fenghua Zhang, Bingwen Feng, Zhihua Xia, Jian Weng, Wei Lu, Bing Chen

Abstract: Various data hiding methods have been suggested to hide secret images within stego images. However, many of them could be easily detected by steganalytic tools due to their large hidden information. In this paper, we enhance the undetectability of image hiding network by mapping latent representation conditional on secret information. We extend the idea of image generation-based steganography and propose a transformer-based image hiding network that can hide a secret image with the same size as the target image. The proposed scheme uses style transferring to help map latent representation. The hiding network of the proposed scheme consists of three modules: encoding, transfer, and synthesis modules. The encoding module extracts the latent representations from content and secret images, the transfer module stylizes the latent representation, and the synthesis module fuses the latent representations to synthesize a target image with the secret image hidden in it. A new synthesis module and corresponding extraction network are developed to enhance recovery accuracy. The proposed scheme shows high image quality on both target images and recovered secret images. Furthermore, it can resist steganalytic tools and thus provide good security.