Mark My Words: Analyzing and Evaluating Language Model Watermarks

• URL: http://arxiv.org/abs/2312.00273v3
• Date: Fri, 11 Oct 2024 19:36:28 GMT
• Title: Mark My Words: Analyzing and Evaluating Language Model Watermarks
• Authors: Julien Piet, Chawin Sitawarin, Vivian Fang, Norman Mu, David Wagner,
• Abstract summary: 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.
• Score: 8.025719866615333
• License:
• Abstract: The capabilities of large language models have grown significantly in recent years and so too have concerns about their misuse. It is important to be able to distinguish machine-generated text from human-authored content. Prior works have proposed numerous schemes to watermark text, which would benefit from a systematic evaluation framework. This work focuses on LLM output watermarking techniques - as opposed to image or model watermarks - and proposes Mark My Words, a comprehensive benchmark for them under different natural language tasks. We focus on three main metrics: quality, size (i.e., the number of tokens needed to detect a watermark), and tamper resistance (i.e., the ability to detect a watermark after perturbing marked text). Current watermarking techniques are nearly practical enough for real-world use: Kirchenbauer et al. [33]'s scheme can watermark models like Llama 2 7B-chat or Mistral-7B-Instruct with no perceivable loss in quality on natural language tasks, the watermark can be detected with fewer than 100 tokens, and their scheme offers good tamper resistance to simple perturbations. However, they struggle to efficiently watermark code generations. We publicly release our benchmark (https://github.com/wagner-group/MarkMyWords).

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)
• De-mark: Watermark Removal in Large Language Models [59.00698153097887]
  We present De-mark, an advanced framework designed to remove n-gram-based watermarks effectively. Our method utilizes a novel querying strategy, termed random selection probing, which aids in assessing the strength of the watermark.
  arXiv  Detail & Related papers  (2024-10-17T17:42:10Z)
• 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)
• Watermarking Language Models for Many Adaptive Users [47.90822587139056]
  We study watermarking schemes for language models with provable guarantees. We introduce multi-user watermarks, which allow tracing model-generated text to individual users. We prove that the undetectable zero-bit scheme of Christ, Gunn, and Zamir (2024) is adaptively robust.
  arXiv  Detail & Related papers  (2024-05-17T22:15:30Z)
• GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick [50.35069175236422]
  Large language models (LLMs) excellently generate human-like text, but also raise concerns about misuse in fake news and academic dishonesty. Decoding-based watermark, particularly the GumbelMax-trick-based watermark(GM watermark), is a standout solution for safeguarding machine-generated texts. We propose a new type of GM watermark, the Logits-Addition watermark, and its three variants, specifically designed to enhance diversity.
  arXiv  Detail & Related papers  (2024-02-20T12:05:47Z)
• 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)
• 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)
• On the Reliability of Watermarks for Large Language Models [95.87476978352659]
  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.
  arXiv  Detail & Related papers  (2023-06-07T17:58:48Z)
• 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.