Learning Image-to-Image Mappings Within a Steganographic Network

Image steganography based on deep neural networks (DNNs) aims to embed secret information into images more rationally. Current DNN-based schemes face two major challenges: security and model deployment. Security issues arise because, in some schemes, a third party who knows the model architecture can extract secret information from stego images. To address this, this paper proposes a novel Learning Image-to-Image Mappings Within a Steganographic Network. For security, the model is trained to map natural images to secret images without modifying the original natural images, and a key is used for embedding and extracting the secret model. For deployment, the secret model is embedded into a stego model that performs ordinary tasks, and can later be extracted using a key. Experiments show that directly transmitting natural images improves steganographic security, the secret model’s performance can be largely recovered before and after steganography, and reconstructed secret images have good visual quality.