发表机构
Seoul National University（首尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出双轴分类法组织扩散生成图像水印方法，并通过三个协议受限案例研究及攻击分类，为系统比较提供框架。
AI 中文摘要
对扩散生成图像进行水印处理需要在来源信号、图像质量、鲁棒性和计算成本之间取得平衡。本工作沿两个轴组织方法：插入机制和主要信号承载表示，并形式化了一个代表性的 $z_T$-Fourier 流水线用于验证和识别。然后，我们利用该分类法构建了三个协议受限的案例研究。第一个案例研究考察了频率完整性、检测、质量和裁剪行为之间的关联。第二个案例研究重新审视了在种子关联和种子无关编辑下的持久性，并提出了一个限定范围的语义印记假设，而不声称存在局部化载体或因果机制。第三个案例研究探讨了单次 VAE 潜变量相位调制，包括其效率、再生鲁棒性以及鲁棒性-质量工作点。最后，我们将四个内容级攻击家族与模型/流水线适应区分开来，提出了相应的评估协议和针对参数调整威胁的可检验猜想，并确定了视频的额外时间扩展。这些分析并未建立通用排名；相反，它们为扩散生成图像的水印系统提供了匹配的、协议感知的比较框架。
英文摘要
Watermarking diffusion-generated images requires balancing provenance signals with image quality, robustness, and computational cost. This work organizes methods along two axes: insertion mechanism and primary signal-bearing representation, and formalizes a representative $z_T$-Fourier pipeline for verification and identification. We then use the taxonomy to structure three protocol-bounded case studies. The first examines associations among frequency integrity, detection, quality, and cropping behavior. The second revisits persistence under seed-linked and seed-independent editing and formulates a scoped Semantic Imprinting Hypothesis without claiming a localized carrier or causal mechanism. The third studies single-shot VAE-latent phase modulation, including its efficiency, regeneration robustness, and robustness--quality operating points. Finally, we separate four content-level attack families from model/pipeline adaptation, propose corresponding evaluation protocols and testable conjectures for parameter-tuning threats, and identify additional temporal extensions for video. These analyses do not establish a universal ranking; instead, they provide a framework for matched, protocol-aware comparisons of watermarking systems for diffusion-generated images.
Comments17 pages, 2 figures. Accepted to the non-archival track of the ECCV 2026 LifeGenIP Workshop. English translation with partial reorganization of our article in Journal of Broadcast Engineering 31(4), 687-699 (2026)
