MorphMark: Flexible Adaptive Watermarking for Large Language Models

• URL: http://arxiv.org/abs/2505.11541v2
• Date: Tue, 20 May 2025 00:24:09 GMT
• Title: MorphMark: Flexible Adaptive Watermarking for Large Language Models
• Authors: Zongqi Wang, Tianle Gu, Baoyuan Wu, Yujiu Yang,
• Abstract summary: Existing watermark methods often struggle with a dilemma: improving watermark effectiveness comes at the cost of reduced text quality.<n>We develop MorphMark method that adaptively adjusts the watermark strength in response to changes in the identified factor.<n>MorphMark achieves a superior resolution of the effectiveness-quality dilemma, while also offering greater flexibility and time and space efficiency.
• Score: 49.3302421751894
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Watermarking by altering token sampling probabilities based on red-green list is a promising method for tracing the origin of text generated by large language models (LLMs). However, existing watermark methods often struggle with a fundamental dilemma: improving watermark effectiveness (the detectability of the watermark) often comes at the cost of reduced text quality. This trade-off limits their practical application. To address this challenge, we first formalize the problem within a multi-objective trade-off analysis framework. Within this framework, we identify a key factor that influences the dilemma. Unlike existing methods, where watermark strength is typically treated as a fixed hyperparameter, our theoretical insights lead to the development of MorphMarka method that adaptively adjusts the watermark strength in response to changes in the identified factor, thereby achieving an effective resolution of the dilemma. In addition, MorphMark also prioritizes flexibility since it is a model-agnostic and model-free watermark method, thereby offering a practical solution for real-world deployment, particularly in light of the rapid evolution of AI models. Extensive experiments demonstrate that MorphMark achieves a superior resolution of the effectiveness-quality dilemma, while also offering greater flexibility and time and space efficiency.

Related papers

• Safe-VAR: Safe Visual Autoregressive Model for Text-to-Image Generative Watermarking [18.251123923955397]
  Autoregressive learning has become a dominant approach for text-to-image generation, offering high efficiency and visual quality.<n>Existing watermarking methods, designed for diffusion models, often struggle to adapt to the sequential nature of VAR models.<n>We propose Safe- VAR, the first watermarking framework specifically designed for autoregressive text-to-image generation.
  arXiv  Detail & Related papers  (2025-03-14T11:45:10Z)
• Improved Unbiased Watermark for Large Language Models [59.00698153097887]
  We introduce MCmark, a family of unbiased, Multi-Channel-based watermarks.<n>MCmark preserves the original distribution of the language model.<n>It offers significant improvements in detectability and robustness over existing unbiased watermarks.
  arXiv  Detail & Related papers  (2025-02-16T21:02:36Z)
• GaussMark: A Practical Approach for Structural Watermarking of Language Models [61.84270985214254]
  GaussMark is a simple, efficient, and relatively robust scheme for watermarking large language models.<n>We show that GaussMark is reliable, efficient, and relatively robust to corruptions such as insertions, deletions, substitutions, and roundtrip translations.
  arXiv  Detail & Related papers  (2025-01-17T22:30:08Z)
• Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach [35.319577498993354]
  We present a novel theoretical framework for watermarking Large Language Models (LLMs)<n>Our approach focuses on maximizing detection performance while maintaining control over the worst-case Type-I error and text distortion.<n>We propose an efficient, model-agnostic, distribution-adaptive watermarking algorithm, utilizing a surrogate model alongside the Gumbel-max trick.
  arXiv  Detail & Related papers  (2024-10-03T18:28:10Z)
• Towards Effective User Attribution for Latent Diffusion Models via Watermark-Informed Blending [54.26862913139299]
  We introduce a novel framework Towards Effective user Attribution for latent diffusion models via Watermark-Informed Blending (TEAWIB)<n> TEAWIB incorporates a unique ready-to-use configuration approach that allows seamless integration of user-specific watermarks into generative models.<n>Experiments validate the effectiveness of TEAWIB, showcasing the state-of-the-art performance in perceptual quality and attribution accuracy.
  arXiv  Detail & Related papers  (2024-09-17T07:52:09Z)
• JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits [76.25962336540226]
  JIGMARK is a first-of-its-kind watermarking technique that enhances robustness through contrastive learning. Our evaluation reveals that JIGMARK significantly surpasses existing watermarking solutions in resilience to diffusion-model edits.
  arXiv  Detail & Related papers  (2024-06-06T03:31:41Z)
• TokenMark: A Modality-Agnostic Watermark for Pre-trained Transformers [67.57928750537185]
  TokenMark is a robust, modality-agnostic, robust watermarking system for pre-trained models.<n>It embeds the watermark by fine-tuning the pre-trained model on a set of specifically permuted data samples.<n>It significantly improves the robustness, efficiency, and universality of model watermarking.
  arXiv  Detail & Related papers  (2024-03-09T08:54:52Z)
• 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)
• Cross-Attention Watermarking of Large Language Models [8.704964543257246]
  New approach to linguistic watermarking of language models is presented. Information is imperceptibly inserted into the output text while preserving its readability and original meaning. Cross-attention mechanism is used to embed watermarks in the text during inference.
  arXiv  Detail & Related papers  (2024-01-12T09:39:50Z)
• Optimizing watermarks for large language models [0.0]
  This paper introduces a systematic approach to the trade-off between watermark identifiability and their impact on the quality of the generated text. For a large class of robust, efficient watermarks, the associated optimal solutions are identified and shown to outperform the currently default watermark.
  arXiv  Detail & Related papers  (2023-12-28T16:10:51Z)
• A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models [65.40460716619772]
  Our research focuses on the importance of a textbfDistribution-textbfPreserving (DiP) watermark. Contrary to the current strategies, our proposed DiPmark simultaneously preserves the original token distribution during watermarking. It is detectable without access to the language model API and prompts (accessible), and is provably robust to moderate changes of tokens.
  arXiv  Detail & Related papers  (2023-10-11T17:57:35Z)

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.