Steganographic Generative Adversarial Networks
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.
Cite
@article{arxiv.1703.05502,
title = {Steganographic Generative Adversarial Networks},
author = {Denis Volkhonskiy and Ivan Nazarov and Evgeny Burnaev},
journal= {arXiv preprint arXiv:1703.05502},
year = {2019}
}
Comments
15 pages, 10 figures, 5 tables, Workshop on Adversarial Training (NIPS 2016, Barcelona, Spain)