arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.10219cs.MMeess.IV
收藏

重新审视基于扩散模型的生成隐写术的安全性

Rethinking Security of Diffusion-based Generative Steganography

Jihao Zhu, Zixuan Chen, Jiali Liu, Lingxiao Yang, Yi Zhou, Weiqi Luo, Xiaohua Xie

AI总结:

本文提出NS-DSer框架,通过分析扩散模型噪声分布与隐写安全性之间的关系,重新评估了基于扩散模型的生成隐写术的安全性。

摘要:

生成图像隐写术是一种在生成的图像中隐藏秘密信息的技术,不依赖于已有的载体图像。最近,一些基于扩散模型的生成图像隐写术(DM-GIS)方法已被引入,这些方法有效对抗传统隐写分析技术。在本文中,我们识别了影响DM-GIS安全性的关键因素,并重新审视现有方法的安全性。具体来说,我们首先概述了当前DM-GIS方法的一般流程,发现扩散模型的噪声空间是主要的嵌入域。进一步,我们分析了DM-GIS安全性和扩散模型噪声分布之间的关系,理论证明任何破坏噪声分布的隐写操作都会损害DM-GIS的安全性。基于这一见解,我们提出了一种基于噪声空间的扩散隐写分析框架(NS-DSer)——一种简单而有效的隐写分析框架,允许在扩散模型的噪声空间中检测DM-GIS生成的图像。我们利用NS-DSer在越来越具有挑战性的检测场景中重新评估现有DM-GIS方法的安全性。实验结果验证了我们对DM-GIS安全性的理论分析,并展示了NS-DSer在各种检测场景中的有效性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑