High-capacity coverless image steganographic scheme based on image synthesis

In this paper, a coverless image steganographic scheme with high capacity is proposed. It can hide a color secret image into a color stego image with the same size. Furthermore, the stego image is synthesized without the aid of any cover images. Since there are no cover modification operations, it reduces the risk of being detected by steganalysis tools. The proposed scheme comprises a stego image synthesis sub-network (SynthesisNet) and a secret image recovery sub-network (RevealNet). In SynthesisNet, we apply the image-to-image translation to implement cross-domain image synthesis. It accepts source and reference images as the inputs, which can be used to customize the semantic and style of the stego image. A mapping between source and reference images is also designed to enhance the authenticity of the stego images. Experiments show that the proposed scheme provides high steganographic undetectability as well as good quality on stego and recovered secret images. Moreover, it can generate stego images with specified contents different from any existing images in the public channel.