Generative Steganography Diffusion

TL;DR

This paper introduces Generative Steganography Diffusion (GSD), a novel invertible diffusion model that generates realistic stego images and guarantees 100% recovery of hidden secret data, outperforming existing methods.

Contribution

The paper proposes StegoDiffusion, an invertible diffusion model for generative steganography that combines high image quality with perfect data recoverability, addressing limitations of GAN and Flow-based methods.

Findings

Achieves 100% secret data recovery.

Produces higher quality stego images than prior methods.

Outperforms existing steganography techniques across metrics.

Abstract

Generative steganography (GS) is an emerging technique that generates stego images directly from secret data. Various GS methods based on GANs or Flow have been developed recently. However, existing GAN-based GS methods cannot completely recover the hidden secret data due to the lack of network invertibility, while Flow-based methods produce poor image quality due to the stringent reversibility restriction in each module. To address this issue, we propose a novel GS scheme called "Generative Steganography Diffusion" (GSD) by devising an invertible diffusion model named "StegoDiffusion". It not only generates realistic stego images but also allows for 100\% recovery of the hidden secret data. The proposed StegoDiffusion model leverages a non-Markov chain with a fast sampling technique to achieve efficient stego image generation. By constructing an ordinary differential equation (ODE) based on the transition probability of the generation process in StegoDiffusion, secret data and stego images can be converted to each other through the approximate solver of ODE -- Euler iteration formula, enabling the use of irreversible but more expressive network structures to achieve model invertibility. Our proposed GSD has the advantages of both reversibility and high performance, significantly outperforming existing GS methods in all metrics.