Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language Models

• URL: http://arxiv.org/abs/2604.10893v1
• Date: Mon, 13 Apr 2026 01:46:51 GMT
• Title: Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language Models
• Abstract summary: Watermarking provides a critical safeguard for large language model (LLM) services.<n>Existing stealing watermark algorithms (SWAs) derive watermark information from watermarked texts.<n>We propose Adaptive Stealing (AS), a novel SWA featuring enhanced design flexibility.
• Score: 7.674428443615767
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Watermarking provides a critical safeguard for large language model (LLM) services by facilitating the detection of LLM-generated text. Correspondingly, stealing watermark algorithms (SWAs) derive watermark information from watermarked texts generated by victim LLMs to craft highly targeted adversarial attacks, which compromise the reliability of watermarks. Existing SWAs rely on fixed strategies, overlooking the non-uniform distribution of stolen watermark information and the dynamic nature of real-world LLM generation processes. To address these limitations, we propose Adaptive Stealing (AS), a novel SWA featuring enhanced design flexibility through Position-Based Seal Construction and Adaptive Selection modules. AS operates by defining multiple attack perspectives derived from distinct activation states of contextually ordered tokens. During attack execution, AS dynamically selects the optimal perspective based on watermark compatibility, generation priority, and dynamic generation relevance. Our experiments demonstrate that AS significantly increases steal efficiency against target watermarks under identical experimental conditions. These findings highlight the need for more robust LLM watermarks to withstand potential attacks. We release our code to the community for future research\footnote{https://github.com/DrankXs/AdaptiveStealingWatermark}.

Related papers

• Vaporizer: Breaking Watermarking Schemes for Large Language Model Outputs [2.5756681494057045]
  We investigate the recent state-of-the-art schemes for watermarking large language models (LLMs) outputs.<n>We analyse the effectiveness of these watermarking techniques against an extensive collection of modified text attacks.
  arXiv  Detail & Related papers  (2026-05-08T09:24:29Z)
• Watermarks for Embeddings-as-a-Service Large Language Models [4.230349220081445]
  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.
  arXiv  Detail & Related papers  (2025-11-28T00:52:40Z)
• AuthenLoRA: Entangling Stylization with Imperceptible Watermarks for Copyright-Secure LoRA Adapters [52.556959321030966]
  Low-Rank Adaptation (LoRA) offers an efficient paradigm for customizing diffusion models.<n>Existing watermarking techniques either target base models or verify LoRA modules themselves.<n>We propose AuthenLoRA, a unified watermarking framework that embeds imperceptible, traceable watermarks directly into the LoRA training process.
  arXiv  Detail & Related papers  (2025-11-26T09:48:11Z)
• Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption [94.887133335656]
  We revisit three classes of watermarking through this lens.<n>emphLLM text watermarking offers modest provider benefit when framed solely as an anti-misuse tool.<n>emphIn-context watermarking (ICW) is tailored for trusted parties, such as conference organizers or educators.
  arXiv  Detail & Related papers  (2025-10-21T06:34:51Z)
• Learning to Watermark: A Selective Watermarking Framework for Large Language Models via Multi-Objective Optimization [17.15048594237333]
  Existing watermarking techniques often face trade-off between watermark detectability and generated text quality.<n>In this paper, we introduce Learning to Watermark (LTW), a novel selective watermarking framework.
  arXiv  Detail & Related papers  (2025-10-13T01:07:38Z)
• 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)
• Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning [34.76886510334969]
  A piggyback attack can maliciously alter the meaning of watermarked text-transforming it into hate speech-while preserving the original watermark.<n>We propose a semantic-aware watermarking algorithm that embeds watermarks into a given target text while preserving its original meaning.
  arXiv  Detail & Related papers  (2025-04-09T04:38:17Z)
• Watermark under Fire: A Robustness Evaluation of LLM Watermarking [40.87788133219292]
  WaterPark is a unified platform that integrates 10 state-of-the-art watermarkers and 12 representative attacks.<n>We conduct a comprehensive assessment of existing watermarkers, unveiling the impact of various design choices on their attack robustness.
  arXiv  Detail & Related papers  (2024-11-20T16:09:22Z)
• 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)
• 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)
• No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices [20.20770405297239]
  We show that common design choices in LLM watermarking schemes make the resulting systems surprisingly susceptible to attack. We propose guidelines and defenses for LLM watermarking in practice.
  arXiv  Detail & Related papers  (2024-02-25T20:24:07Z)
• Adaptive Text Watermark for Large Language Models [8.100123266517299]
  It is challenging to generate high-quality watermarked text while maintaining strong security, robustness, and the ability to detect watermarks without prior knowledge of the prompt or model. This paper proposes an adaptive watermarking strategy to address this problem.
  arXiv  Detail & Related papers  (2024-01-25T03:57:12Z)
• WatME: Towards Lossless Watermarking Through Lexical Redundancy [58.61972059246715]
  This study assesses the impact of watermarking on different capabilities of large language models (LLMs) from a cognitive science lens. We introduce Watermarking with Mutual Exclusion (WatME) to seamlessly integrate watermarks.
  arXiv  Detail & Related papers  (2023-11-16T11:58:31Z)

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.