Invertible Mosaic Image Hiding Network for Very Large Capacity Image Steganography

TL;DR

This paper introduces InvMIHNet, a novel invertible network that conceals up to 16 secret images within a cover image by using a mosaic approach, achieving high capacity and quality in image steganography.

Contribution

The paper proposes a new invertible mosaic image hiding network that enables very large capacity steganography by concealing a single mosaic image, reducing interference among multiple secret images.

Findings

Successfully conceals and reveals up to 16 secret images.

Outperforms state-of-the-art methods in imperceptibility and accuracy.

Uses fewer parameters and less memory than existing approaches.

Abstract

The existing image steganography methods either sequentially conceal secret images or conceal a concatenation of multiple images. In such ways, the interference of information among multiple images will become increasingly severe when the number of secret images becomes larger, thus restrict the development of very large capacity image steganography. In this paper, we propose an Invertible Mosaic Image Hiding Network (InvMIHNet) which realizes very large capacity image steganography with high quality by concealing a single mosaic secret image. InvMIHNet consists of an Invertible Image Rescaling (IIR) module and an Invertible Image Hiding (IIH) module. The IIR module works for downscaling the single mosaic secret image form by spatially splicing the multiple secret images, and the IIH module then conceal this mosaic image under the cover image. The proposed InvMIHNet successfully conceal and reveal up to 16 secret images with a small number of parameters and memory consumption. Extensive experiments on ImageNet-1K, COCO and DIV2K show InvMIHNet outperforms state-of-the-art methods in terms of both the imperceptibility of stego image and recover accuracy of secret image.