StegNet: Mega Image Steganography Capacity with Deep Convolutional Network
This addresses the need for high-capacity steganography in secure communication, though it is incremental as it builds on existing deep learning methods.
The paper tackles the problem of low payload capacity in image steganography by using a deep convolutional neural network to hide same-size images, achieving a decoding rate of 98.2% or 23.57 bpp while altering only 0.76% of the cover image on average.
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.