StegNet: Mega Image Steganography Capacity with Deep Convolutional Network

TL;DR

This paper introduces StegNet, a deep learning-based image steganography method that achieves high payload capacity and decoding accuracy while maintaining robustness against statistical detection.

Contribution

It presents an end-to-end deep convolutional neural network approach for high-capacity image steganography with robust decoding and minimal cover image alteration.

Findings

Achieves 98.2% decoding accuracy at 23.57 bpp

Changes only 0.76% of cover image on average

Embedded images remain robust to statistical analysis

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.