SteganoGAN: High Capacity Image Steganography with GANs (2019-01-12T00:00:00.000000Z)

TL;DR

This paper proposes 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 the model.

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 this https URL.

Authors

K. Veeramachaneni

7 papers

Alfredo Cuesta-Infante

3 papers

K. Zhang

1 papers

TL;DR

Abstract

Authors

References43 items

HiDDeN: Hiding Data With Deep Networks

StegNet: Mega Image Steganography Capacity with Deep Convolutional Network

Hiding Images in Plain Sight: Deep Steganography

An overview of steganography techniques applied to the protection of biometric data

Progressive Growing of GANs for Improved Quality, Stability, and Variation

Automatic Steganographic Distortion Learning Using a Generative Adversarial Network

NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study

Wasserstein Generative Adversarial Networks

Deep Learning Hierarchical Representations for Image Steganalysis

BEGAN: Boundary Equilibrium Generative Adversarial Networks

Generating steganographic images via adversarial training

Stacked Generative Adversarial Networks

High-Resolution Image Inpainting Using Multi-scale Neural Patch Synthesis

Energy-based Generative Adversarial Network

Densely Connected Convolutional Networks

Deep Residual Learning for Image Recognition

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Frequency domain QR code based image steganography using Fresnelet transform

StegExpose - A Tool for Detecting LSB Steganography

A new cost function for spatial image steganography

Generative Adversarial Nets

Microsoft COCO: Common Objects in Context

Universal distortion function for steganography in an arbitrary domain

Stego image quality and the reliability of PSNR

Using High-Dimensional Image Models to Perform Highly Undetectable Steganography

A Model of Digital Contents Access Control System Using Steganographic Information Hiding Scheme

Secure transmission of medical records using high capacity steganography

Image quality assessment: from error visibility to structural similarity

Code wars: Steganography, signals intelligence, and terrorism

Detection of LSB steganography via sample pair analysis

On steganalysis of random LSB embedding in continuous-tone images

Reliable detection of LSB steganography in color and grayscale images

Attacks on Steganographic Systems

Polynomial Codes Over Certain Finite Fields

A Survey on Image Steganography and Steganalysis

A Survey on Image Steganography and Steganalysis

Gradient-based learning applied to document recognition

Filter Banks

A survey of steganographic techniques

For each of these trained models, we generate a set of 1,000 steganographic images

SteganoGAN

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names