高斯香农:基于通信的高精度扩散模型水印技术
Gaussian Shannon: High-Precision Diffusion Model Watermarking Based on Communication
AI总结:
本文提出Gaussian Shannon水印框架,通过将扩散过程视为噪声通信信道,实现鲁棒追踪和精确位恢复,适用于无损元数据应用。
摘要:
扩散模型生成高质量图像但面临版权侵犯和虚假信息风险。水印技术是追踪和验证AI生成内容的关键防御手段。然而,现有方法依赖于阈值检测,仅支持模糊匹配,无法精确恢复结构化水印数据位,不适用于离线验证或需要无损元数据的应用(如许可说明)。为解决此问题,本文提出Gaussian Shannon水印框架,将扩散过程视为噪声通信信道,实现鲁棒追踪和精确位恢复。我们的方法在初始高斯噪声中嵌入水印,无需微调或质量损失。我们识别了两种信道干扰类型,即局部位翻转和全局随机失真,并设计了一种结合纠错码和多数投票的级联防御机制。这确保了语义负载的可靠端到端传输。在三个Stable Diffusion变种和七种扰动类型上的实验表明,Gaussian Shannon在位级精度上达到最先进的水平,同时保持高真正阳性率,使在实际部署中能够实现可信的权利归属。源代码已发布在:https://github.com/Rambo-Yi/Gaussian-Shannon
英文摘要:
Diffusion models generate high-quality images but pose serious risks like copyright violation and disinformation. Watermarking is a key defense for tracing and authenticating AI-generated content. However, existing methods rely on threshold-based detection, which only supports fuzzy matching and cannot recover structured watermark data bit-exactly, making them unsuitable for offline verification or applications requiring lossless metadata (e.g., licensing instructions). To address this problem, in this paper, we propose Gaussian Shannon, a watermarking framework that treats the diffusion process as a noisy communication channel and enables both robust tracing and exact bit recovery. Our method embeds watermarks in the initial Gaussian noise without fine-tuning or quality loss. We identify two types of channel interference, namely local bit flips and global stochastic distortions, and design a cascaded defense combining error-correcting codes and majority voting. This ensures reliable end-to-end transmission of semantic payloads. Experiments across three Stable Diffusion variants and seven perturbation types show that Gaussian Shannon achieves state-of-the-art bit-level accuracy while maintaining a high true positive rate, enabling trustworthy rights attribution in real-world deployment. The source code have been made available at: https://github.com/Rambo-Yi/Gaussian-Shannon
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。