PRIS: Practical robust invertible network for image steganography

TL;DR

PRIS introduces a robust invertible neural network-based method for image steganography that enhances resistance to distortions like noise and compression, considering rounding errors with a new gradient approximation, outperforming existing techniques.

Contribution

The paper presents PRIS, a novel invertible neural network framework with enhancement modules and a gradient approximation to improve robustness and practicality in image steganography.

Findings

PRIS outperforms state-of-the-art methods in robustness.

The method effectively handles rounding errors in practical scenarios.

Experimental results demonstrate improved robustness and practicability.

Abstract

Image steganography is a technique of hiding secret information inside another image, so that the secret is not visible to human eyes and can be recovered when needed. Most of the existing image steganography methods have low hiding robustness when the container images affected by distortion. Such as Gaussian noise and lossy compression. This paper proposed PRIS to improve the robustness of image steganography, it based on invertible neural networks, and put two enhance modules before and after the extraction process with a 3-step training strategy. Moreover, rounding error is considered which is always ignored by existing methods, but actually it is unavoidable in practical. A gradient approximation function (GAF) is also proposed to overcome the undifferentiable issue of rounding distortion. Experimental results show that our PRIS outperforms the state-of-the-art robust image steganography method in both robustness and practicability. Codes are available at https://github.com/yanghangAI/PRIS, demonstration of our model in practical at http://yanghang.site/hide/.