WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off

• URL: http://arxiv.org/abs/2403.04808v3
• Date: Fri, 18 Oct 2024 07:05:57 GMT
• Title: WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off
• Abstract summary: Watermarking is a technical means to dissuade malfeasant usage of Large Language Models. This paper proposes a novel watermarking scheme, so-called WaterMax, that enjoys high detectability while sustaining the quality of the generated text.
• Score: 10.926616117284983
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Watermarking is a technical means to dissuade malfeasant usage of Large Language Models. This paper proposes a novel watermarking scheme, so-called WaterMax, that enjoys high detectability while sustaining the quality of the generated text of the original LLM. Its new design leaves the LLM untouched (no modification of the weights, logits, temperature, or sampling technique). WaterMax balances robustness and complexity contrary to the watermarking techniques of the literature inherently provoking a trade-off between quality and robustness. Its performance is both theoretically proven and experimentally validated. It outperforms all the SotA techniques under the most complete benchmark suite. Code available at https://github.com/eva-giboulot/WaterMax.

Related papers

• WaterMoE: Expert-Routing-based Watermarking for High Fidelity and Efficiency [0.0]
  Large language models (LLMs) have achieved remarkable success but raise growing concerns about content provenance and misuse.<n>WaterMoE embeds watermarking signals through controlled perturbation into the expert selection at each router.<n>WaterMoE consistently outperforms state-of-the-art watermarking methods on a benchmark.
  arXiv  Detail & Related papers  (2026-07-14T06:18:05Z)
• EditMark: Watermarking Large Language Models based on Model Editing [76.04893766374221]
  We propose EditMark, the first watermarking method that leverages model editing to embed a training-free, stealthy, and performance-lossless watermark.<n>Experiments indicate that EditMark can embed 32-bit watermarks into LLMs within 20 seconds with a watermark extraction success rate of 100%.
  arXiv  Detail & Related papers  (2025-10-18T06:25:17Z)
• HeavyWater and SimplexWater: Watermarking Low-Entropy Text Distributions [9.08291061147965]
  Large language model (LLM) watermarks enable authentication of text provenance, curb misuse of machine-generated text, and promote trust in AI systems.<n>LLM watermarking is challenging in low-entropy generation tasks - such as coding - where next-token predictions are near-deterministic.<n>Our goal is to understand how to most effectively use random side information in order to maximize the likelihood of watermark detection and minimize the distortion of generated text.
  arXiv  Detail & Related papers  (2025-06-06T13:52:34Z)
• 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. 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)
• Robust Detection of Watermarks for Large Language Models Under Human Edits [27.678152860666163]
  We introduce a new method in the form of a truncated goodness-of-fit test for detecting watermarked text under human edits. We prove that the Tr-GoF test achieves optimality in robust detection of the Gumbel-GoF watermark. We also show that the Tr-GoF test attains the highest detection efficiency rate in a certain regime of moderate text modifications.
  arXiv  Detail & Related papers  (2024-11-21T06:06:04Z)
• WaterPark: A Robustness Assessment of Language Model Watermarking [40.50648910458236]
  We develop WaterPark, a unified platform that integrates 10 state-of-the-art watermarkers and 12 representative attacks. We conduct a comprehensive assessment of existing watermarkers, unveiling the impact of various design choices on their attack robustness. Using a generic detector alongside a watermark-specific detector improves the security of vulnerable watermarkers.
  arXiv  Detail & Related papers  (2024-11-20T16:09:22Z)
• Can Watermarked LLMs be Identified by Users via Crafted Prompts? [55.460327393792156]
  This work is the first to investigate the imperceptibility of watermarked Large Language Models (LLMs) We design an identification algorithm called Water-Probe that detects watermarks through well-designed prompts. Experiments show that almost all mainstream watermarking algorithms are easily identified with our well-designed prompts.
  arXiv  Detail & Related papers  (2024-10-04T06:01:27Z)
• Universally Optimal Watermarking Schemes for LLMs: from Theory to Practice [35.319577498993354]
  Large Language Models (LLMs) boosts human efficiency but also poses misuse risks. We propose a novel theoretical framework for watermarking LLMs. We jointly optimize both the watermarking scheme and detector to maximize detection performance.
  arXiv  Detail & Related papers  (2024-10-03T18:28:10Z)
• Less is More: Sparse Watermarking in LLMs with Enhanced Text Quality [27.592486717044455]
  We present a novel type of watermark, Sparse Watermark, which aims to mitigate this trade-off by applying watermarks to a small subset of generated tokens distributed across the text. Our experimental results demonstrate that the proposed watermarking scheme achieves high detectability while generating text that outperforms previous watermarking methods in quality across various tasks.
  arXiv  Detail & Related papers  (2024-07-17T18:52:12Z)
• 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)
• 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)
• Turning Your Strength into Watermark: Watermarking Large Language Model via Knowledge Injection [66.26348985345776]
  We propose a novel watermarking method for large language models (LLMs) based on knowledge injection. In the watermark embedding stage, we first embed the watermarks into the selected knowledge to obtain the watermarked knowledge. In the watermark extraction stage, questions related to the watermarked knowledge are designed, for querying the suspect LLM. Experiments show that the watermark extraction success rate is close to 100% and demonstrate the effectiveness, fidelity, stealthiness, and robustness of our proposed method.
  arXiv  Detail & Related papers  (2023-11-16T03:22:53Z)
• Unbiased Watermark for Large Language Models [67.43415395591221]
  This study examines how significantly watermarks impact the quality of model-generated outputs. It is possible to integrate watermarks without affecting the output probability distribution. The presence of watermarks does not compromise the performance of the model in downstream tasks.
  arXiv  Detail & Related papers  (2023-09-22T12:46:38Z)
• An Unforgeable Publicly Verifiable Watermark for Large Language Models [84.2805275589553]
  Current watermark detection algorithms require the secret key used in the watermark generation process, making them susceptible to security breaches and counterfeiting during public detection. We propose an unforgeable publicly verifiable watermark algorithm named UPV that uses two different neural networks for watermark generation and detection, instead of using the same key at both stages.
  arXiv  Detail & Related papers  (2023-07-30T13:43:27Z)
• 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)

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.