arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.04878cs.CR
收藏

插件隐藏:可证明且可调节的扩散生成隐写术

Plug-and-Hide: Provable and Adjustable Diffusion Generative Steganography

School of Computer Science and Engineering, Sun Yat-sen University(中山大学计算机科学与工程学院);Zhongshan School of Medicine, Sun Yat-sen University(中山大学中山医学院)

Jiahao Zhu, Zixuan Chen, Jiali Liu, Weiqi Luo, Yi Zhou, Xiaohua Xie

AI总结:

提出PA-B2G方法,实现可证明且可调节的扩散生成隐写术,兼顾图像质量、安全性和提取可靠性。

摘要:

基于扩散模型的生成图像隐写术(DM-GIS)是一种新兴范式,利用扩散模型的生成能力在不需预存载体图像的情况下隐藏秘密信息。在本文中,我们识别出在DM-GIS框架内存在图像质量、隐写术安全性和提取可靠性之间的根本性权衡。基于这一见解,我们提出了PA-B2G,即可证明且可调节的位到高斯映射。理论上,PA-B2G保证了任意长度的位序列可以被可逆地映射到纯高斯噪声;实践中,它能够精细控制图像保真度、安全性和提取准确性之间的平衡。通过将PA-B2G与概率流常微分方程(PF-ODEs)结合,我们建立了秘密位流与隐写图像之间的可逆映射。PA-B2G是模型无关的,可以无缝集成到主流扩散模型中,无需额外训练或微调,使其也适用于扩散模型水印技术。广泛的实验验证了我们对DM-GIS内在权衡的理论分析,并展示了我们的方法能够灵活支持任意负载,同时实现具有竞争力的图像质量和安全性。此外,我们的方法在水印应用中表现出对有损处理的强鲁棒性,突显了其实际应用价值。

英文摘要:

Diffusion model-based generative image steganography (DM-GIS) is an emerging paradigm that leverages the generative power of diffusion models to conceal secret messages without requiring pre-existing cover images. In this paper, we identify a fundamental trade-off between stego image quality, steganographic security, and extraction reliability within the DM-GIS framework. Drawing on this insight, we propose \textbf{PA-B2G}, a \textbf{P}rovable and \textbf{A}djustable \textbf{B}it-to-\textbf{G}aussian mapping. Theoretically, PA-B2G guarantees the reversible encoding of arbitrary-length bit sequences into pure Gaussian noise; practically, it enables fine-grained control over the balance between image fidelity, security, and extraction accuracy. By integrating PA-B2G with probability-flow ordinary differential equations (PF-ODEs), we establish a theoretically invertible mapping between secret bitstreams and stego images. PA-B2G is model-agnostic and can be seamlessly integrated into mainstream diffusion models without additional training or fine-tuning, making it also suitable for diffusion model watermarking. Extensive experiments validate our theoretical analysis of the inherent DM-GIS trade-offs and demonstrate that our method flexibly supports arbitrary payloads while achieving competitive image quality and security. Furthermore, our method exhibits strong resilience to lossy processing in watermarking applications, highlighting its practical utility.

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。

↑