On the Reliability of Watermarks for Large Language Models

• URL: http://arxiv.org/abs/2306.04634v4
• Date: Wed, 1 May 2024 21:20:36 GMT
• Title: On the Reliability of Watermarks for Large Language Models
• Authors: John Kirchenbauer, Jonas Geiping, Yuxin Wen, Manli Shu, Khalid Saifullah, Kezhi Kong, Kasun Fernando, Aniruddha Saha, Micah Goldblum, Tom Goldstein,
• Abstract summary: We study the robustness of watermarked text after it is re-written by humans, paraphrased by a non-watermarked LLM, or mixed into a longer hand-written document. We find that watermarks remain detectable even after human and machine paraphrasing. We also consider a range of new detection schemes that are sensitive to short spans of watermarked text embedded inside a large document.
• Score: 95.87476978352659
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As LLMs become commonplace, machine-generated text has the potential to flood the internet with spam, social media bots, and valueless content. Watermarking is a simple and effective strategy for mitigating such harms by enabling the detection and documentation of LLM-generated text. Yet a crucial question remains: How reliable is watermarking in realistic settings in the wild? There, watermarked text may be modified to suit a user's needs, or entirely rewritten to avoid detection. We study the robustness of watermarked text after it is re-written by humans, paraphrased by a non-watermarked LLM, or mixed into a longer hand-written document. We find that watermarks remain detectable even after human and machine paraphrasing. While these attacks dilute the strength of the watermark, paraphrases are statistically likely to leak n-grams or even longer fragments of the original text, resulting in high-confidence detections when enough tokens are observed. For example, after strong human paraphrasing the watermark is detectable after observing 800 tokens on average, when setting a 1e-5 false positive rate. We also consider a range of new detection schemes that are sensitive to short spans of watermarked text embedded inside a large document, and we compare the robustness of watermarking to other kinds of detectors.

Related papers

• Revisiting the Robustness of Watermarking to Paraphrasing Attacks [10.68370011459729]
  Many recent watermarking techniques modify the output probabilities of LMs to embed a signal in the generated output that can later be detected. We show that with access to only a limited number of generations from a black-box watermarked model, we can drastically increase the effectiveness of paraphrasing attacks to evade watermark detection.
  arXiv  Detail & Related papers  (2024-11-08T02:22:30Z)
• Efficiently Identifying Watermarked Segments in Mixed-Source Texts [35.437251393372954]
  We propose two novel methods for partial watermark detection. First, we develop a geometry cover detection framework aimed at determining whether there is a watermark segment in long text. Second, we introduce an adaptive online learning algorithm to pinpoint the precise location of watermark segments within the text.
  arXiv  Detail & Related papers  (2024-10-04T16:58:41Z)
• 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)
• 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)
• On the Learnability of Watermarks for Language Models [80.97358663708592]
  We ask whether language models can directly learn to generate watermarked text. We propose watermark distillation, which trains a student model to behave like a teacher model. We find that models can learn to generate watermarked text with high detectability.
  arXiv  Detail & Related papers  (2023-12-07T17:41:44Z)
• Mark My Words: Analyzing and Evaluating Language Model Watermarks [8.025719866615333]
  This work focuses on output watermarking techniques, as opposed to image or model watermarks. We focus on three main metrics: quality, size (i.e., the number of tokens needed to detect a watermark), and tamper resistance.
  arXiv  Detail & Related papers  (2023-12-01T01:22:46Z)
• I Know You Did Not Write That! A Sampling Based Watermarking Method for Identifying Machine Generated Text [0.0]
  We propose a new watermarking method to detect machine-generated texts. Our method embeds a unique pattern within the generated text. We show how watermarking affects textual quality and compare our proposed method with a state-of-the-art watermarking method.
  arXiv  Detail & Related papers  (2023-11-29T20:04:57Z)
• 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)
• Can AI-Generated Text be Reliably Detected? [54.670136179857344]
  Unregulated use of LLMs can potentially lead to malicious consequences such as plagiarism, generating fake news, spamming, etc. Recent works attempt to tackle this problem either using certain model signatures present in the generated text outputs or by applying watermarking techniques. In this paper, we show that these detectors are not reliable in practical scenarios.
  arXiv  Detail & Related papers  (2023-03-17T17:53:19Z)
• 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)

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.