Recent Advances of Image Steganography with Generative Adversarial Networks
arXiv:1907.01886
Abstract
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.
39 pages, 26 figures
References in corpus (10)
- Conditional Generative Adversarial Nets
- Energy-based Generative Adversarial Network
- A Kernel Method for the Two-Sample Problem
- Mode Regularized Generative Adversarial Networks
- CycleGAN, a Master of Steganography
- Learning to Protect Communications with Adversarial Neural Cryptography
- Adversarial Generation of Natural Language
- SteganoGAN: High Capacity Image Steganography with GANs
- Recurrent Topic-Transition GAN for Visual Paragraph Generation
- Coverless Information Hiding Based on Generative adversarial networks