An Novel Image Steganography Method via Deep Convolutional Generative Adversarial Networks

In this paper, we propose a novel image SWE method based on the deep convolutional generative adversarial networks (DCGANs). We map the secret information into a noise vector, and then use the trained generator neural network model to generate the carrier image based on the noise vector. During the process of image generation, there is no modification or embedding operation.