SteganoGAN: High Capacity Image Steganography with GANs

Kevin Alex Zhang, Alfredo Cuesta-Infante, Lei Xu, Kalyan Veeramachaneni
1/12/2019
cs.CVcs.LGcs.MM

Official code: DAI-Lab/SteganoGAN (395 stars, MIT, last commit 2023-03-23).

Abstract

Image steganography is a procedure for hiding messages inside pictures. While other techniques such as cryptography aim to prevent adversaries from reading the secret message, steganography aims to hide the presence of the message itself. In this paper, we propose a novel technique for hiding arbitrary binary data in images using generative adversarial networks which allow us to optimize the perceptual quality of the images produced by our model. We show that our approach achieves state-of-the-art payloads of 4.4 bits per pixel, evades detection by steganalysis tools, and is effective on images from multiple datasets. To enable fair comparisons, we have released an open source library that is available online at https://github.com/DAI-Lab/SteganoGAN.

View on arXivView PDF

Code Implementations(1)

DAI-Lab/SteganoGANOfficial100%
MIT

SteganoGAN is a tool for creating steganographic images using adversarial training.

395103Shell, Python3 years agoMIT
generative-adversarial-networkssteganography

Similar Papers

A Novel Approach to Image Steganography Using Generative Adversarial Networks

89% match2024

Generative Steganography Network

89% match2022

Diffusion-Stego: Training-free Diffusion Generative Steganography via Message Projection

87% match2023

Image Generation Network for Covert Transmission in Online Social Network

86% match2022

Securing Fixed Neural Network Steganography

85% match2023

Purified and Unified Steganographic Network

84% match1 repo432024

Cite this paper

@article{zhang2019steganogan,
  title  = {SteganoGAN: High Capacity Image Steganography with GANs},
  author = {Kevin Alex Zhang and Alfredo Cuesta-Infante and Lei Xu and Kalyan Veeramachaneni},
  year   = {2019},
  eprint = {1901.03892},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1901.03892}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1901.03892.svg)](https://codeofpaper.com/paper/1901.03892)

Discussion