Image steganography based on generative implicit neural representation

TL;DR

This paper introduces a novel image steganography method using generative implicit neural representations, enabling resolution-independent data hiding with high extraction accuracy and reduced computational costs.

Contribution

It presents a new approach that uses continuous functional expressions for data embedding, overcoming resolution constraints and simplifying the message extraction process.

Findings

Achieves 3 seconds embedding time for 64x64 images

Provides 100% message extraction accuracy

Supports diverse multimedia cover images

Abstract

In the realm of advanced steganography, the scale of the model typically correlates directly with the resolution of the fundamental grid, necessitating the training of a distinct neural network for message extraction. This paper proposes an image steganography based on generative implicit neural representation. This approach transcends the constraints of image resolution by portraying data as continuous functional expressions. Notably, this method permits the utilization of a diverse array of multimedia data as cover images, thereby broadening the spectrum of potential carriers. Additionally, by fixing a neural network as the message extractor, we effectively redirect the training burden to the image itself, resulting in both a reduction in computational overhead and an enhancement in steganographic speed. This approach also circumvents potential transmission challenges associated with the message extractor. Experimental findings reveal that this methodology achieves a commendable optimization efficiency, achieving a completion time of just 3 seconds for 64x64 dimensional images, while concealing only 1 bpp of information. Furthermore, the accuracy of message extraction attains an impressive mark of 100%.