Image steganography aims to securely embed secret information into cover images. Until now, adaptive embedding algorithms such as S-UNIWARD or Mi-POD, were among the most secure and most often used methods for image steganography. With the arrival of deep learning and more specifically, Generative Adversarial Networks (GAN), new steganography techniques have appeared. Among them is the 3-player game approach, where three networks compete against each other. In this paper, we propose three different architectures based on the 3-player game. The first architecture is proposed as a rigorous alternative to two recent publications. The second takes into account stego noise power. Finally, our third architecture enriches the second one with a better interaction between embedding and extracting networks. Our method achieves better results compared to existing works Hayes and Danezis (2017), Zhu et al. (2018), and paves the way for future research on this topic.

图像隐写术旨在将秘密信息安全地嵌入封面图像中。到目前为止，自适应嵌入算法（例如S-UNIWARD或Mi-POD）是图像隐写术中最安全，最常用的方法之一。随着深度学习的到来，更具体地说，是生成对抗网络（GAN），新的隐写技术出现了。其中包括3人游戏方法，其中三个网络相互竞争。在本文中，我们基于3人游戏提出了三种不同的体系结构。提出了第一种体系结构，作为最近两个出版物的严格替代方案。第二个考虑了隐身噪声功率。最后，我们的第三个架构通过嵌入和提取网络之间的更好交互来丰富了第二个架构。与现有的Hayes和Danezis（2017）等人的工作相比，我们的方法取得了更好的结果。（2018），并为该主题的未来研究铺平了道路。