SteganoGAN: High Capacity Image Steganography with GANs

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.

References in corpus (5)

• Energy-based Generative Adversarial Network
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Generating Steganographic Images via Adversarial Training
• StegNet: Mega Image Steganography Capacity with Deep Convolutional Network
• StegExpose - A Tool for Detecting LSB Steganography

Cited by in corpus (12)

• A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU
• StegaStamp: Invisible Hyperlinks in Physical Photographs
• Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganography
• Robust Data Hiding Using Inverse Gradient Attention
• Recent Advances of Image Steganography with Generative Adversarial Networks
• Decentralized Attribution of Generative Models
• Distortion Agnostic Deep Watermarking
• Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderings
• GANash -- A GAN approach to steganography
• Robust Invisible Hyperlinks in Physical Photographs Based on 3D Rendering Attacks
• VisCode: Embedding Information in Visualization Images using Encoder-Decoder Network
• Multitask Identity-Aware Image Steganography via Minimax Optimization