Steganography using a 3-player game - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier
Journal Articles Journal of Visual Communication and Image Representation Year : 2020

Steganography using a 3-player game

Mehdi Yedroudj
Frédéric Comby
Marc Chaumont

Abstract

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 GSIVAT, HiDDeN, and paves the way for future research on this topic.
Fichier principal
Vignette du fichier
JVCIR2020 - Steganography using a 3-player game - YEDROUDJ-COMBY-CHAUMONT.pdf (2.97 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

lirmm-02937056 , version 1 (12-09-2020)

Identifiers

Cite

Mehdi Yedroudj, Frédéric Comby, Marc Chaumont. Steganography using a 3-player game. Journal of Visual Communication and Image Representation, 2020, 72, pp.#102910. ⟨10.1016/j.jvcir.2020.102910⟩. ⟨lirmm-02937056⟩
111 View
89 Download

Altmetric

Share

More