给文生图编辑加可追溯、可解释的隐形水印，防篡改且难移除。
AngelFingerprint: A Traceable, Explainable, and White-Box Stealthy Watermark for Text-Guided Image Editing
- 将编辑提示的文本嵌入模型权重，通过LoRA实现
- 在MagicBrush上实现86%提示召回准确率，远超传统方法
- 适合需要图像溯源与防伪的AI生成内容场景
文生图扩散模型编辑引发虚假信息担忧，可靠图像溯源至关重要。现有水印方法多采用固定标识，无法解释修改内容或对应提示词，且在开源白盒环境下易被定位并移除。针对此问题，我们提出AngelFingerprint，一种具备编辑可追溯性、可解释性与白盒隐蔽性的新型水印框架。该方法将编辑提示的CLIP文本嵌入通过LoRA整合进扩散模型权重中，仅需图像像素即可通过提取器恢复该嵌入。这一语义载荷可说明具体修改内容，而权重内嵌设计使其在全白盒攻击下仍难以检测和分离。两项关键技术支撑：速度对齐锚点保障编辑质量，特定频域滤波确保水印不可见但可恢复且鲁棒。在MagicBrush数据集上，提取器在200类提示检索中达到86%的top-1准确率，显著优于提示反演的20%。
原文摘要 · Abstract (English)
Text-guided diffusion editing raises disinformation concerns, making reliable image provenance essential. While watermarks are commonly used for this purpose, most methods carry a fixed ID that cannot explain what was changed and which prompt produced it. Furthermore, under open-source white-box access, attackers can easily locate and remove watermarks added as separate modules. Targeting this setting, we propose AngelFingerprint, a novel watermarking framework ensuring edit traceability, explainability, and white-box stealthiness. It integrates a LoRA into the diffusion model to embed the editing prompt's CLIP text embedding directly into the model's weights. An extractor then recovers this embedding from the image pixels alone. This semantic payload explains the edit, while the weight-integrated design makes it hard to detect and isolate even under full white-box access. Two techniques make this possible: a velocity-alignment anchor that preserves edit quality, and a specially designed frequency filter that keeps the watermark imperceptible yet recoverable and robust. On the MagicBrush dataset, our extractor achieves $86\%$ top-1 accuracy in a 200-way prompt retrieval, versus $20\%$ for prompt inversion.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。