Rethinking Security of Diffusion-based Generative Steganography

TL;DR

This paper critically examines the security of diffusion-based generative steganography, revealing vulnerabilities related to noise distribution and proposing a new detection framework that effectively identifies steganographic images.

Contribution

It provides a theoretical analysis linking noise distribution disruption to security breaches and introduces NS-DSer, a novel steganalyzer for diffusion model noise space detection.

Findings

The noise space is the primary embedding domain in DM-GIS.

Disrupting noise distribution compromises DM-GIS security.

NS-DSer effectively detects DM-GIS images across various scenarios.

Abstract

Generative image steganography is a technique that conceals secret messages within generated images, without relying on pre-existing cover images. Recently, a number of diffusion model-based generative image steganography (DM-GIS) methods have been introduced, which effectively combat traditional steganalysis techniques. In this paper, we identify the key factors that influence DM-GIS security and revisit the security of existing methods. Specifically, we first provide an overview of the general pipelines of current DM-GIS methods, finding that the noise space of diffusion models serves as the primary embedding domain. Further, we analyze the relationship between DM-GIS security and noise distribution of diffusion models, theoretically demonstrating that any steganographic operation that disrupts the noise distribution compromise DM-GIS security. Building on this insight, we propose a Noise Space-based Diffusion Steganalyzer (NS-DSer)-a simple yet effective steganalysis framework allowing for detecting DM-GIS generated images in the diffusion model noise space. We reevaluate the security of existing DM-GIS methods using NS-DSer across increasingly challenging detection scenarios. Experimental results validate our theoretical analysis of DM-GIS security and show the effectiveness of NS-DSer across diverse detection scenarios.