paper-with-me

홈 › Papers

From Essence to Defense: Adaptive Semantic-aware Watermarking for Embedding-as-a-Service Copyright Protection

2025-12-18 · Hao Li, Yubing Ren, Yanan Cao, Yingjie Li, Fang Fang, Xuebin Wang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2512.16439

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language Understanding

Similar Papers 제목 키워드 기반

Removing Watermarks with Partial Regeneration using Semantic Information

2025-05-13 · Krti Tallam, John Kevin Cava, Caleb Geniesse, N. Benjamin Erichson 외

As AI-generated imagery becomes ubiquitous, invisible watermarks have emerged as a primary line of defense for copyright and provenance. The newest watermarking schemes embed semantic signals - content-aware patterns tha…

SSIMZero Shot Segmentation

Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark

2024-11-14 · Zekun Fei, Biao Yi, Jianing Geng, Ruiqi He 외

Embedding-as-a-Service (EaaS) has emerged as a successful business pattern but faces significant challenges related to various forms of copyright infringement, particularly, the API misuse and model extraction attacks. V…

Model extraction

DualGuard: Dual-stream Large Language Model Watermarking Defense against Paraphrase and Spoofing Attack

2025-12-18 · Hao Li, Yubing Ren, Yanan Cao, Yingjie Li 외 arxiv

With the rapid development of cloud-based services, large language models have become increasingly accessible through various web platforms. However, this accessibility has also led to growing risks of model abuse. LLM w…

AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Models

2026-02-10 · Yue Li, Xin Yi, Dongsheng Shi, Yongyi Cui 외 arxiv

Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in large vision language models (LVLMs). However, vision-agnostic watermarks may introduce visually irrelevant …

Visual Grounding

Steganalysis on Digital Watermarking: Is Your Defense Truly Impervious?

2024-06-13 · Pei Yang, Hai Ci, Yiren Song, Mike Zheng Shou

Digital watermarking techniques are crucial for copyright protection and source identification of images, especially in the era of generative AI models. However, many existing watermarking methods, particularly content-a…

Steganalysis