Lune

ACL Findings2025

Robust and Minimally Invasive Watermarking for EaaS

Zongqi Wang, Baoyuan Wu, Jingyuan Deng, Yujiu Yang

Abstract

Embeddings as a Service (EaaS) is emerging as a crucial role in AI applications.Unfortunately, EaaS is vulnerable to model extraction attacks, highlighting the urgent need for copyright protection.Although some preliminary works propose applying embedding watermarks to protect EaaS, recent research reveals that these watermarks can be easily removed.Hence, it is crucial to inject robust watermarks resistant to watermark removal attacks.Existing watermarking methods typically inject a target embedding into embeddings through linear interpolation when the text contains triggers.However, this mechanism results in each watermarked embedding having the same component, which makes the watermark easy to identify and eliminate.Motivated by this, in this paper, we propose a novel embedding-specific watermarking (ESpeW) mechanism to offer robust copyright protection for EaaS.Our approach involves injecting unique, yet readily identifiable watermarks into each embedding.Watermarks inserted by ESpeW are designed to maintain a significant distance from one another and to avoid sharing common components, thus making it significantly more challenging to remove the watermarks.Moreover, ESpeW is minimally invasive, as it reduces the impact on embeddings to less than 1%, setting a new milestone in watermarking for EaaS.Extensive experiments on four popular datasets demonstrate that ESpeW can even watermark successfully against a highly aggressive removal strategy without sacrificing the quality of embeddings.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation cites SimCSE: Simple Contrastive Learning of Sentence Embeddings
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. ErrorTrace: A Black-Box Traceability Mechanism Based on Model Family Error SpaceChuanchao Zang, Xiangtao Meng, Wenyu Chen, Tianshuo Cong et al.NeurIPS 2025 · 4 citations

Builds on22

  1. SimCSE: Simple Contrastive Learning of Sentence EmbeddingsTianyu Gao, Xingcheng Yao, Danqi ChenEMNLP 2021 · 2,496 citations
  2. A Simple and Effective Pruning Approach for Large Language ModelsMingjie Sun, Zhuang Liu, Anna Bair, J. Zico KolterICLR 2024 · 794 citations
  3. M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge DistillationJianlyu Chen, Shitao Xiao, Peitian Zhang, Kun Luo et al.ACL Findings 2024 · 762 citations
  4. Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base EmbeddingsApoorv Saxena, Aditay Tripathi, Partha P. TalukdarACL 2020 · 488 citations
  5. MIND: A Large-scale Dataset for News RecommendationFangzhao Wu, Ying Qiao, Jiun-Hung Chen, Chuhan Wu et al.ACL 2020 · 454 citations

Related papers

  1. RegionMarker: A Region-Triggered Semantic Watermarking Framework for Embedding-as-a-Service Copyright ProtectionShufan Yang, Zifeng Cheng, Zhiwei Jiang, Yafeng Yin et al.AAAI 2026 · 1 citation
  2. WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation WatermarksAnudeex Shetty, Qiongkai Xu, Jey Han LauACL 2025 · 7 citations
  3. Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor WatermarkWenjun Peng, Jingwei Yi, Fangzhao Wu, Shangxi Wu et al.ACL 2023 · 39 citations
  4. Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS WatermarkZekun Fei, Biao Yi, Jianing Geng, Ruiqi He et al.EMNLP Findings 2025
  5. GuardEmb: Dynamic Watermark for Safeguarding Large Language Model Embedding Service Against Model Stealing AttackLiaoyaqi Wang, Minhao ChengEMNLP Findings 2024 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines