From Essence to Defense: Adaptive Semantic-aware Watermarking for Embedding-as-a-Service Copyright Protection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909968795435008 |
|---|---|
| author | Li, Hao Ren, Yubing Cao, Yanan Li, Yingjie Fang, Fang Wang, Xuebin |
| author_facet | Li, Hao Ren, Yubing Cao, Yanan Li, Yingjie Fang, Fang Wang, Xuebin |
| contents | Benefiting from the superior capabilities of large language models in natural language understanding and generation, Embeddings-as-a-Service (EaaS) has emerged as a successful commercial paradigm on the web platform. However, prior studies have revealed that EaaS is vulnerable to imitation attacks. Existing methods protect the intellectual property of EaaS through watermarking techniques, but they all ignore the most important properties of embedding: semantics, resulting in limited harmlessness and stealthiness. To this end, we propose SemMark, a novel semantic-based watermarking paradigm for EaaS copyright protection. SemMark employs locality-sensitive hashing to partition the semantic space and inject semantic-aware watermarks into specific regions, ensuring that the watermark signals remain imperceptible and diverse. In addition, we introduce the adaptive watermark weight mechanism based on the local outlier factor to preserve the original embedding distribution. Furthermore, we propose Detect-Sampling and Dimensionality-Reduction attacks and construct four scenarios to evaluate the watermarking method. Extensive experiments are conducted on four popular NLP datasets, and SemMark achieves superior verifiability, diversity, stealthiness, and harmlessness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_16439 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Essence to Defense: Adaptive Semantic-aware Watermarking for Embedding-as-a-Service Copyright Protection Li, Hao Ren, Yubing Cao, Yanan Li, Yingjie Fang, Fang Wang, Xuebin Cryptography and Security Computation and Language Benefiting from the superior capabilities of large language models in natural language understanding and generation, Embeddings-as-a-Service (EaaS) has emerged as a successful commercial paradigm on the web platform. However, prior studies have revealed that EaaS is vulnerable to imitation attacks. Existing methods protect the intellectual property of EaaS through watermarking techniques, but they all ignore the most important properties of embedding: semantics, resulting in limited harmlessness and stealthiness. To this end, we propose SemMark, a novel semantic-based watermarking paradigm for EaaS copyright protection. SemMark employs locality-sensitive hashing to partition the semantic space and inject semantic-aware watermarks into specific regions, ensuring that the watermark signals remain imperceptible and diverse. In addition, we introduce the adaptive watermark weight mechanism based on the local outlier factor to preserve the original embedding distribution. Furthermore, we propose Detect-Sampling and Dimensionality-Reduction attacks and construct four scenarios to evaluate the watermarking method. Extensive experiments are conducted on four popular NLP datasets, and SemMark achieves superior verifiability, diversity, stealthiness, and harmlessness. |
| title | From Essence to Defense: Adaptive Semantic-aware Watermarking for Embedding-as-a-Service Copyright Protection |
| topic | Cryptography and Security Computation and Language |
| url | https://arxiv.org/abs/2512.16439 |