Log In Sign Up

Recent Advances of Image Steganography with Generative Adversarial Networks

by   Jia Liu, et al.

In the past few years, the Generative Adversarial Network (GAN) which proposed in 2014 has achieved great success. GAN has achieved many research results in the field of computer vision and natural language processing. Image steganography is dedicated to hiding secret messages in digital images, and has achieved the purpose of covert communication. Recently, research on image steganography has demonstrated great potential for using GAN and neural networks. In this paper we review different strategies for steganography such as cover modification, cover selection and cover synthesis by GANs, and discuss the characteristics of these methods as well as evaluation metrics and provide some possible future research directions in image steganography.


An Introduction to Image Synthesis with Generative Adversarial Nets

There has been a drastic growth of research in Generative Adversarial Ne...

Generative Steganography with Kerckhoffs' Principle based on Generative Adversarial Networks

The distortion in steganography that usually comes from the modification...

Generative Adversarial Networks: A Survey Towards Private and Secure Applications

Generative Adversarial Networks (GAN) have promoted a variety of applica...

Steganography using a 3 player game

Image steganography aims to securely embed secret information into cover...

Steganography GAN: Cracking Steganography with Cycle Generative Adversarial Networks

For as long as humans have participated in the act of communication, con...

Deep Graph Generators: A Survey

Deep generative models have achieved great success in areas such as imag...

Relational Data Synthesis using Generative Adversarial Networks: A Design Space Exploration

The proliferation of big data has brought an urgent demand for privacy-p...