A Unified Framework for LLM Watermarks

• URL: http://arxiv.org/abs/2602.06754v1
• Date: Fri, 06 Feb 2026 15:00:30 GMT
• Title: A Unified Framework for LLM Watermarks
• Authors: Thibaud Gloaguen, Robin Staab, Nikola Jovanović, Martin Vechev,
• Abstract summary: We show that most existing and widely used watermarking schemes can in fact be derived from a principled constrained optimization problem.<n>Our framework also provides a principled approach for designing novel watermarking schemes tailored to specific requirements.
• Score: 9.515480957792542
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM watermarks allow tracing AI-generated texts by inserting a detectable signal into their generated content. Recent works have proposed a wide range of watermarking algorithms, each with distinct designs, usually built using a bottom-up approach. Crucially, there is no general and principled formulation for LLM watermarking. In this work, we show that most existing and widely used watermarking schemes can in fact be derived from a principled constrained optimization problem. Our formulation unifies existing watermarking methods and explicitly reveals the constraints that each method optimizes. In particular, it highlights an understudied quality-diversity-power trade-off. At the same time, our framework also provides a principled approach for designing novel watermarking schemes tailored to specific requirements. For instance, it allows us to directly use perplexity as a proxy for quality, and derive new schemes that are optimal with respect to this constraint. Our experimental evaluation validates our framework: watermarking schemes derived from a given constraint consistently maximize detection power with respect to that constraint.

Related papers

• Detecting Post-generation Edits to Watermarked LLM Outputs via Combinatorial Watermarking [51.417096446156926]
  We introduce a new task: detecting post-generation edits locally made to watermarked LLM outputs.<n>We propose a pattern-based watermarking framework, which partitions the vocabulary into disjoint subsets and embeds the watermark.<n>We evaluate our method on open-source LLMs across a variety of editing scenarios, demonstrating strong empirical performance in edit localization.
  arXiv  Detail & Related papers  (2025-10-02T03:33:12Z)
• In-Context Watermarks for Large Language Models [71.29952527565749]
  In-Context Watermarking (ICW) embeds watermarks into generated text solely through prompt engineering.<n>We investigate four ICW strategies at different levels of granularity, each paired with a tailored detection method.<n>Our experiments validate the feasibility of ICW as a model-agnostic, practical watermarking approach.
  arXiv  Detail & Related papers  (2025-05-22T17:24:51Z)
• Entropy-Guided Watermarking for LLMs: A Test-Time Framework for Robust and Traceable Text Generation [58.85645136534301]
  Existing watermarking schemes for sampled text often face trade-offs between maintaining text quality and ensuring robust detection against various attacks.<n>We propose a novel watermarking scheme that improves both detectability and text quality by introducing a cumulative watermark entropy threshold.
  arXiv  Detail & Related papers  (2025-04-16T14:16:38Z)
• Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoning [58.57194301645823]
  Large language models (LLMs) are increasingly integrated into real-world personalized applications.<n>The valuable and often proprietary nature of the knowledge bases used in RAG introduces the risk of unauthorized usage by adversaries.<n>Existing methods that can be generalized as watermarking techniques to protect these knowledge bases typically involve poisoning or backdoor attacks.<n>We propose name for harmless' copyright protection of knowledge bases.
  arXiv  Detail & Related papers  (2025-02-10T09:15:56Z)
• Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach [53.32564762183639]
  We introduce a novel, unified theoretical framework for watermarking Large Language Models (LLMs)<n>Our approach aims to maximize detection performance while maintaining control over the worst-case false positive rate (FPR) and distortion on text quality.<n>We propose a distortion-free, distribution-adaptive watermarking algorithm (DAWA) that leverages a surrogate model for model-agnosticism and efficiency.
  arXiv  Detail & Related papers  (2024-10-03T18:28:10Z)
• Topic-Based Watermarks for Large Language Models [46.71493672772134]
  We propose a lightweight, topic-guided watermarking scheme for Large Language Model (LLM) output.<n>Our method achieves comparable perplexity to industry-leading systems, including Google's SynthID-Text.
  arXiv  Detail & Related papers  (2024-04-02T17:49:40Z)
• A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules [27.382399391266564]
  We introduce a framework for reasoning about the statistical efficiency of watermarks and powerful detection rules.<n>We derive optimal detection rules for watermarks under our framework.
  arXiv  Detail & Related papers  (2024-04-01T17:03:41Z)
• Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models [31.062753031312006]
  Large language models generate high-quality responses with potential misinformation. Watermarking is pivotal in this context, which involves embedding hidden markers in texts. We introduce a novel multi-objective optimization (MOO) approach for watermarking. Our method simultaneously achieves detectability and semantic integrity.
  arXiv  Detail & Related papers  (2024-02-28T05:43:22Z)
• 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)
• WMFormer++: Nested Transformer for Visible Watermark Removal via Implict Joint Learning [68.00975867932331]
  Existing watermark removal methods mainly rely on UNet with task-specific decoder branches. We introduce an implicit joint learning paradigm to holistically integrate information from both branches. The results demonstrate our approach's remarkable superiority, surpassing existing state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2023-08-20T07:56:34Z)
• Provable Robust Watermarking for AI-Generated Text [41.5510809722375]
  We propose a robust and high-quality watermark method, Unigram-Watermark. We prove that our watermark method enjoys guaranteed generation quality, correctness in watermark detection, and is robust against text editing and paraphrasing.
  arXiv  Detail & Related papers  (2023-06-30T07:24:32Z)
• Watermarking Images in Self-Supervised Latent Spaces [75.99287942537138]
  We revisit watermarking techniques based on pre-trained deep networks, in the light of self-supervised approaches. We present a way to embed both marks and binary messages into their latent spaces, leveraging data augmentation at marking time.
  arXiv  Detail & Related papers  (2021-12-17T15:52:46Z)

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.