Geometry-Aware Localized Watermarking for Copyright Protection in Embedding-as-a-Service
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917403035697152 |
|---|---|
| author | Chen, Zhimin Liang, Xiaojie Xu, Wenbo Liu, Yuxuan Lu, Wei |
| author_facet | Chen, Zhimin Liang, Xiaojie Xu, Wenbo Liu, Yuxuan Lu, Wei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_11344 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Geometry-Aware Localized Watermarking for Copyright Protection in Embedding-as-a-Service Chen, Zhimin Liang, Xiaojie Xu, Wenbo Liu, Yuxuan Lu, Wei Cryptography and Security Computation and Language 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. |
| title | Geometry-Aware Localized Watermarking for Copyright Protection in Embedding-as-a-Service |
| topic | Cryptography and Security Computation and Language |
| url | https://arxiv.org/abs/2604.11344 |