Global Sketch-Based Watermarking for Diffusion Language Models

• URL: http://arxiv.org/abs/2606.04486v1
• Date: Wed, 03 Jun 2026 06:08:58 GMT
• Title: Global Sketch-Based Watermarking for Diffusion Language Models
• Abstract summary: We propose a watermark for masked diffusion language models that controls a global, vector-valued sketch representation of the text.<n>Compared to context-dependent watermarking, the sketch formulation decouples detection from the local contexts seen during generation.<n>We analyze the distortion, soundness, and robustness properties of the method.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Watermarking methods for language models have been studied extensively in the autoregressive setting, where tokens are generated sequentially. These works largely focus on local-context schemes that perturb the next token's distribution as a function of its preceding tokens. In diffusion language models, distributions over many unresolved positions are jointly sampled, allowing additive statistics of the entire sequence to be tractable during generation. We propose a watermark for masked diffusion language models that controls a global, vector-valued sketch representation of the text. Compared to context-dependent watermarking, the sketch formulation decouples detection from the local contexts seen during generation, resulting in an order-agnostic statistic and a watermarking rule which does not manifest as a simple token bias. We analyze the distortion, soundness, and robustness properties of the method.

Related papers

• DenMark: Robust Semantic Watermarking for Diffusion Language Models [56.836684262732994]
  DenMark is a semantic watermarking framework for diffusion language models (DLMs)<n>It injects key-dependent signals directly into the DLM denoising process.<n>It partitions the output into fixed token regions and uses temporary rollouts as semantic lookahead.<n>For detection, DenMark uses calibrated scanning over candidate unit sizes to remain robust to boundary shifts introduced by semantic attacks.
  arXiv  Detail & Related papers  (2026-09-13T03:37:48Z)
• Optimal Watermark Localization in Mixed-Source Large Language Model Texts [41.92651100461471]
  Watermarking provides a principled way to authenticate text generated by large language models (LLMs)<n>In practice, the final text may be mixed-source, with watermark evidence surviving at only a subset of token positions after rewriting, insertion, deletion, or paraphrasing.<n>We formulate localization as a token-level multiple-testing problem based on pivotal statistics, with a latent indicator recording whether watermark dependence survives at each position.
  arXiv  Detail & Related papers  (2026-08-14T21:41:50Z)
• Selective Disclosure Watermarking for Large Language Models [16.579884795891754]
  We propose Hierarchical Vocabulary Routing (HeRo), a watermarking framework that enables selective disclosure of embedded metadata.<n>We show that the proposed scheme preserves the unbiasedness of the underlying sampling process and thus maintains text quality.
  arXiv  Detail & Related papers  (2026-07-06T17:32:01Z)
• Watermarking Discrete Diffusion Language Models [17.991665184843562]
  We introduce the first watermarking method for discrete diffusion models by applying the distribution-preserving Gumbel-max trick at every diffusion step.<n>We experimentally demonstrate and analytically prove that our scheme is distortion-free with an exponentially decaying probability of false detection in the token sequence length.
  arXiv  Detail & Related papers  (2025-11-03T21:43:44Z)
• 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)
• Downstream Trade-offs of a Family of Text Watermarks [25.408313192999504]
  We evaluate the performance of LLMs watermarked using three different strategies over a diverse suite of tasks. We find that watermarks can cause significant drops in LLMs' effective utility across all tasks. Our findings highlight the trade-offs that users should be cognizant of when using watermarked models.
  arXiv  Detail & Related papers  (2023-11-16T11:44:58Z)
• Improving the Generation Quality of Watermarked Large Language Models via Word Importance Scoring [81.62249424226084]
  Token-level watermarking inserts watermarks in the generated texts by altering the token probability distributions. This watermarking algorithm alters the logits during generation, which can lead to a downgraded text quality. We propose to improve the quality of texts generated by a watermarked language model by Watermarking with Importance Scoring (WIS)
  arXiv  Detail & Related papers  (2023-11-16T08:36:00Z)
• 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)
• Watermarking Text Generated by Black-Box Language Models [103.52541557216766]
  A watermark-based method was proposed for white-box LLMs, allowing them to embed watermarks during text generation. A detection algorithm aware of the list can identify the watermarked text. We develop a watermarking framework for black-box language model usage scenarios.
  arXiv  Detail & Related papers  (2023-05-14T07:37:33Z)
• A Watermark for Large Language Models [84.95327142027183]
  We propose a watermarking framework for proprietary language models. The watermark can be embedded with negligible impact on text quality. It can be detected using an efficient open-source algorithm without access to the language model API or parameters.
  arXiv  Detail & Related papers  (2023-01-24T18:52:59Z)
• SpaText: Spatio-Textual Representation for Controllable Image Generation [61.89548017729586]
  SpaText is a new method for text-to-image generation using open-vocabulary scene control. In addition to a global text prompt that describes the entire scene, the user provides a segmentation map. We show its effectiveness on two state-of-the-art diffusion models: pixel-based and latent-conditional-based.
  arXiv  Detail & Related papers  (2022-11-25T18:59:10Z)

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.