跳到正文
arXiv cs.AI· Chihcheng Hsieh, Yang Song, Flora Salim, Martin Bell, Jacinto C. Nascimento, Catarina Moreira·· 2 小时前AI 评分37

SpiderMark:面向生成式 AI 的混合水印方案,结合算法注入与学习式验证

SpiderMark: Hybrid Watermarking for Generative AI via Algorithmic Injection and Learning-Based Verification

AI 导读

SpiderMark 是一种面向扩散模型的混合水印框架,在初始潜在噪声的傅里叶表示中嵌入蛛网结构图案,并训练带 PSNR 与 L1 辅助线索的轻量 ResNet-18 验证器输出水印置信度,无需修改预训练扩散模型权重。在九种评估条件中的八种取得最高固定阈值 Accuracy,对未见过的 COCO 提示词无需重训练仍保持检测能力,且 CLIP 相似度与 FID 差异较小。

正文 · 原文

View PDF HTML (experimental)

Abstract:The proliferation of diffusion-based generative models has intensified the need for reliable methods to trace and verify the provenance of AI-generated images. Existing watermarking approaches for diffusion models typically rely on isotropic frequency patterns and handcrafted detection metrics, which are prone to directional vulnerability and threshold instability across diverse image transformations. We propose SpiderMark, a hybrid watermarking framework that combines algorithmic frequency-domain injection with learning-based probabilistic verification, requiring no modifications to pretrained diffusion model weights. SpiderMark embeds a structured spider-web pattern, comprising radial spokes and concentric polygonal rings, into the Fourier representation of the initial latent noise, and trains a lightweight ResNet-18 verifier augmented with auxiliary similarity cues (PSNR and L1) to produce a continuous watermark confidence score for watermark detection. Across nine evaluation conditions, SpiderMark achieves the highest fixed-threshold Accuracy in eight, while retaining strong detection on unseen COCO prompts without verifier retraining. CLIP similarity and FID measurements show that these detection gains are accompanied by small measured differences in prompt alignment and distributional image quality. SpiderMark establishes that structured watermark geometry and learned probabilistic verification can be unified into a single, practical framework, bridging the gap between imperceptibility, robustness, and real-world verifiability for generative AI content attribution.
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.24200 [cs.CV]
  (or arXiv:2611.24200v1 [cs.CV] for this version)
  https://doi.org/10.48550/arXiv.2611.24200

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Catarina Moreira [view email]
[v1] Wed, 18 Nov 2026 10:36:51 UTC (24,711 KB)

来源:arXiv cs.AI · arxiv.org