SteganoGAN: High Capacity Image Steganography with GANs

TL;DR

This paper introduces SteganoGAN, a GAN-based method for high-capacity image steganography that achieves state-of-the-art payloads while remaining undetectable by steganalysis tools.

Contribution

The paper presents a novel GAN-based approach for image steganography that significantly improves payload capacity and detection evasion, with an open-source implementation for fair comparison.

Findings

Achieves 4.4 bits per pixel payload

Evasion of steganalysis detection

Effective across multiple datasets

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.