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

2026-04-13

AI Summary

This work addresses the vulnerability of Embedding-as-a-Service to model stealing and copyright infringement, where existing watermarking techniques struggle to simultaneously achieve robustness, utility, and verifiability. The authors propose GeoMark, a novel framework that uniquely integrates geometric awareness with a localized watermarking mechanism. By constructing explicit-margin geometric anchors through manifold embedding and injecting watermarks only within adaptive local neighborhoods, GeoMark decouples trigger location from ownership attribution, thereby mitigating false positives and fragility. Experiments across four benchmark datasets demonstrate that GeoMark preserves downstream task performance and geometric fidelity while exhibiting strong robustness against paraphrasing, dimensional perturbations, and CSE attacks, achieving stable verification with low false-positive rates.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Adversarial Learning & Robustness
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Security and Privacy: Data transparency and provenance

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.

Problem

• Embedding-as-a-Service
• watermarking
• copyright protection
• robustness
• false positives

Innovation

• geometry-aware watermarking
• localized triggering
• embedding-as-a-service
• robust copyright protection
• adaptive neighborhood