Steganography using a 3 player game
This work addresses image steganography for secure communication, presenting incremental improvements over recent deep learning techniques.
The paper tackles the problem of securely embedding secret information into images by proposing three new architectures based on a 3-player game approach, achieving better results compared to existing methods like GSIVAT and HiDDeN.
Image steganography aims to securely embed secret information into cover images. Until now, adaptive embedding algorithms such as S-UNIWARD or Mi-POD, are among the most secure and most used methods for image steganography. With the arrival of deep learning and more specifically the Generative Adversarial Networks (GAN), new techniques have appeared. Among these techniques, there is the 3 player game approaches, 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 the embedding and extracting networks. Our method achieves better results compared to the existing works GSIVAT, HiDDeN, and paves the way for future research on this topic.