Generative Adversarial Networks for Image Steganography

Denis Volkhonskiy, Boris Borisenko, Evgeny Burnaev

Abstract: Steganography is collection of methods to hide secret information ("payload") within non-secret information ("container"). Its counterpart, Steganalysis, is the practice of determining if a message contains a hidden payload, and recovering it if possible. Presence of hidden payloads is typically detected by a binary classifier. In the present study, we propose a new model for generating image-like containers based on Deep Convolutional Generative Adversarial Networks (DCGAN). This approach allows to generate more setganalysis-secure message embedding using standard steganography algorithms. Experiment results demonstrate that the new model successfully deceives the steganography analyzer, and for this reason, can be used in steganographic applications.

TL;DR: We consider a new type of GAN model and apply it to secure image steganography

Conflicts: hse.ru, iitp.ru, skoltech.ru

Keywords: Computer vision, Deep learning, Unsupervised Learning, Applications, Supervised Learning