StegNet: Mega Image Steganography Capacity with Deep Convolutional Network

Abstract

Traditional image steganography often leans interests towards safely embedding hidden information into cover images with payload capacity almost neglected. This paper combines recent deep convolutional neural network methods with image-into-image steganography. It successfully hides the same size images with a decoding rate of 98.2% or bpp (bits per pixel) of 23.57 by changing only 0.76% of the cover image on average. Our method directly learns end-to-end mappings between the cover image and the embedded image and between the hidden image and the decoded image. We~further show that our embedded image, while with mega payload capacity, is still robust to statistical analysis.

https://github.com/adamcavendish/StegNet-Mega-Image-Steganography-Capacity-with-Deep-Convolutional-Network

References in corpus (9)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Deep Residual Learning for Image Recognition
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Squeeze-and-Excitation Networks
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Highway Networks
• Xception: Deep Learning with Depthwise Separable Convolutions
• StegExpose - A Tool for Detecting LSB Steganography
• SSGAN: Secure Steganography Based on Generative Adversarial Networks

Cited by in corpus (10)

• SteganoGAN: High Capacity Image Steganography with GANs
• StegaStamp: Invisible Hyperlinks in Physical Photographs
• DeepFormableTag: End-to-end Generation and Recognition of Deformable Fiducial Markers
• Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganography
• SCReedSolo: A Secure and Robust LSB Image Steganography Framework with Randomized Symmetric Encryption and Reed-Solomon Coding
• PixelSteganalysis: Destroying Hidden Information with a Low Degree of Visual Degradation
• From Image to Imuge: Immunized Image Generation
• DeepMorph: A System for Hiding Bitstrings in Morphable Vector Drawings
• VisCode: Embedding Information in Visualization Images using Encoder-Decoder Network
• Multitask Identity-Aware Image Steganography via Minimax Optimization