Watermarks for Embeddings-as-a-Service Large Language Models

• URL: http://arxiv.org/abs/2512.03079v1
• Date: Fri, 28 Nov 2025 00:52:40 GMT
• Title: Watermarks for Embeddings-as-a-Service Large Language Models
• Authors: Anudeex Shetty,
• Abstract summary: This thesis focuses on defending against imitation attacks by investigating E watermarks.<n>Existing E watermarks can be removed through paraphrasing text when attackers clone the model during imitation attacks.<n>We propose a novel watermarking technique, which employs linear transformation embeddings.
• Score: 4.230349220081445
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have demonstrated exceptional capabilities in natural language understanding and generation. Based on these LLMs, businesses have started to provide Embeddings-as-a-Service (EaaS), offering feature extraction capabilities (in the form of text embeddings) that benefit downstream natural language processing tasks. However, prior research has demonstrated that EaaS is vulnerable to imitation attacks, where an attacker clones the service's model in a black-box manner without access to the model's internal workings. In response, watermarks have been added to the text embeddings to protect the intellectual property of EaaS providers by allowing them to check for model ownership. This thesis focuses on defending against imitation attacks by investigating EaaS watermarks. To achieve this goal, we unveil novel attacks and propose and validate new watermarking techniques. Firstly, we show that existing EaaS watermarks can be removed through paraphrasing the input text when attackers clone the model during imitation attacks. Our study illustrates that paraphrasing can effectively bypass current state-of-the-art EaaS watermarks across various attack setups (including different paraphrasing techniques and models) and datasets in most instances. This demonstrates a new vulnerability in recent EaaS watermarking techniques. Subsequently, as a countermeasure, we propose a novel watermarking technique, WET (Watermarking EaaS with Linear Transformation), which employs linear transformation of the embeddings. Watermark verification is conducted by applying a reverse transformation and comparing the similarity between recovered and original embeddings. We demonstrate its robustness against paraphrasing attacks with near-perfect verifiability. We conduct detailed ablation studies to assess the significance of each component and hyperparameter in WET.

Related papers

• LLM Watermark Evasion via Bias Inversion [24.543675977310357]
  We propose the emphBias-Inversion Rewriting Attack (BIRA), which is theoretically motivated and model-agnostic.<n>BIRA weakens the watermark signal by suppressing the logits of likely watermarked tokens during rewriting, without any knowledge of the underlying watermarking scheme.
  arXiv  Detail & Related papers  (2025-09-27T00:24:57Z)
• Character-Level Perturbations Disrupt LLM Watermarks [64.60090923837701]
  We formalize the system model for Large Language Model (LLM) watermarking.<n>We characterize two realistic threat models constrained on limited access to the watermark detector.<n>We demonstrate character-level perturbations are significantly more effective for watermark removal under the most restrictive threat model.<n> Experiments confirm the superiority of character-level perturbations and the effectiveness of the Genetic Algorithm (GA) in removing watermarks under realistic constraints.
  arXiv  Detail & Related papers  (2025-09-11T02:50:07Z)
• Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark [5.2431999629987]
  Various studies have proposed backdoor-based watermarking schemes to protect the copyright of E services.<n>In this paper, we reveal that previous watermarking schemes possess semantic-independent characteristics and propose the Semantic Perturbation Attack (SPA)<n>Our theoretical and experimental analysis demonstrate that this semantic-independent nature makes current watermarking schemes vulnerable to adaptive attacks that exploit semantic perturbations tests to bypass watermark verification.
  arXiv  Detail & Related papers  (2024-11-14T11:06:34Z)
• Revisiting the Robustness of Watermarking to Paraphrasing Attacks [10.68370011459729]
  Many recent watermarking techniques modify the output probabilities of LMs to embed a signal in the generated output that can later be detected. We show that with access to only a limited number of generations from a black-box watermarked model, we can drastically increase the effectiveness of paraphrasing attacks to evade watermark detection.
  arXiv  Detail & Related papers  (2024-11-08T02:22:30Z)
• Robust and Minimally Invasive Watermarking for EaaS [50.08021440235581]
  Embeds as a Service (Eding) is emerging as a crucial role in AI applications.<n>Eding is vulnerable to model extraction attacks, highlighting the need for copyright protection.<n>We propose a novel embedding-specific watermarking (ESpeW) mechanism to offer robust copyright protection for Eding.
  arXiv  Detail & Related papers  (2024-10-23T04:34:49Z)
• WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks [28.992750031041744]
  We show that existing E watermarks can be removed by paraphrasing when attackers clone the model.<n>We propose a novel watermarking technique that involves linearly transforming the embeddings.
  arXiv  Detail & Related papers  (2024-08-29T18:59:56Z)
• Large Language Model Watermark Stealing With Mixed Integer Programming [51.336009662771396]
  Large Language Model (LLM) watermark shows promise in addressing copyright, monitoring AI-generated text, and preventing its misuse. Recent research indicates that watermarking methods using numerous keys are susceptible to removal attacks. We propose a novel green list stealing attack against the state-of-the-art LLM watermark scheme.
  arXiv  Detail & Related papers  (2024-05-30T04:11:17Z)
• WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection [7.660430606056949]
  We propose a new protocol to make the removal of watermarks more challenging by incorporating multiple possible watermark directions. Our defense approach, WARDEN, notably increases the stealthiness of watermarks and has been empirically shown to be effective against CSE attack.
  arXiv  Detail & Related papers  (2024-03-03T10:39:27Z)
• Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark [58.60940048748815]
  Companies have begun to offer Embedding as a Service (E) based on large language models (LLMs) E is vulnerable to model extraction attacks, which can cause significant losses for the owners of LLMs. We propose an Embedding Watermark method called EmbMarker that implants backdoors on embeddings.
  arXiv  Detail & Related papers  (2023-05-17T08:28:54Z)
• Exploring Structure Consistency for Deep Model Watermarking [122.38456787761497]
  The intellectual property (IP) of Deep neural networks (DNNs) can be easily stolen'' by surrogate model attack. We propose a new watermarking methodology, namely structure consistency'', based on which a new deep structure-aligned model watermarking algorithm is designed.
  arXiv  Detail & Related papers  (2021-08-05T04:27:15Z)
• Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models [72.9364216776529]
  We propose a novel watermark removal attack from a different perspective. We design a simple yet powerful transformation algorithm by combining imperceptible pattern embedding and spatial-level transformations. Our attack can bypass state-of-the-art watermarking solutions with very high success rates.
  arXiv  Detail & Related papers  (2020-09-18T09:14:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.