Geometry-Aware Localized Watermarking for Copyright Protection in Embedding-as-a-Service

TL;DR

GeoMark is a geometry-aware localized watermarking framework for embedding-as-a-service that enhances robustness and accuracy in copyright verification while preserving utility.

Contribution

It introduces a novel geometry-separated, localized watermarking method that decouples watermark trigger location from ownership attribution.

Findings

GeoMark maintains high utility and geometric fidelity.

It achieves robust copyright verification against paraphrasing and perturbation.

GeoMark reduces false positives and improves verification stability.

Abstract

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.