提出几何感知水印框架，解决嵌入服务版权保护的鲁棒性难题
Geometry-Aware Localized Watermarking for Copyright Protection in Embedding-as-a-Service
- 利用嵌入流形中的自然目标点，构建带显式间距的几何锚点
- 仅在自适应局部邻域内激活水印，实现精准触发与集中归属
- 在四种数据集上抗改写、降维和聚类选择消除攻击，误报率低
嵌入即服务（EaaS）已成为自然语言与多媒体应用的重要语义基础设施，但极易遭受模型盗用和版权侵犯。现有EaaS水印方法面临鲁棒性-效用-可验证性之间的根本矛盾：基于触发的方法对改写敏感，基于变换的方法对维度扰动敏感，基于区域的方法可能因偶然几何相似产生误报。为此，我们提出GeoMark，一种面向EaaS版权保护的几何感知局部水印框架。GeoMark采用嵌入流形中的自然目标作为共享水印基准，构建具有明确目标-锚点间距的几何分离锚点，并仅在自适应局部邻域内激活水印注入。该设计将水印触发位置与所有权归属解耦，实现局部触发与集中归属。在四个基准数据集上的实验表明，GeoMark在保持下游任务性能和几何保真度的同时，能有效抵御改写、维度扰动及CSE（聚类、选择、消除）攻击，验证稳定性提升且误报风险低。
原文摘要 · Abstract (English)
Embedding-as-a-Service (EaaS) has become an important semantic infrastructure for natural language and multimedia applications, but it is highly vulnerable to model stealing and copyright infringement. Existing EaaS watermarking methods face a fundamental robustness--utility--verifiability tension: trigger-based methods are fragile to paraphrasing, transformation-based methods are sensitive to dimensional perturbation, and region-based methods may incur false positives due to coincidental geometric affinity. To address this problem, we propose GeoMark, a geometry-aware localized watermarking framework for EaaS copyright protection. GeoMark uses a natural in-manifold embedding as a shared watermark target, constructs geometry-separated anchors with explicit target--anchor margins, and activates watermark injection only within adaptive local neighborhoods. This design decouples where watermarking is triggered from what ownership is attributed to, achieving localized triggering and centralized attribution. Experiments on four benchmark datasets show that GeoMark preserves downstream utility and geometric fidelity while maintaining robust copyright verification under paraphrasing, dimensional perturbation, and CSE (Clustering, Selection, Elimination) attacks, with improved verification stability and low false-positive risk.
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。