# Steganography using a 3 player game

## TL;DR

This paper introduces three novel deep learning architectures based on a three-player game framework for image steganography, outperforming existing methods and advancing the state of the art in secure information embedding.

## Contribution

It proposes three new GAN-based architectures for image steganography, improving upon recent models and incorporating stego noise power and enhanced network interactions.

## Key findings

- Achieves better results than GSIVAT, HiDDeN.
- Introduces architectures that improve embedding and extraction.
- Paves the way for future research in GAN-based steganography.

## Abstract

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.