Large Language Model Watermark Stealing With Mixed Integer Programming

• URL: http://arxiv.org/abs/2405.19677v1
• Date: Thu, 30 May 2024 04:11:17 GMT
• Title: Large Language Model Watermark Stealing With Mixed Integer Programming
• Authors: Zhaoxi Zhang, Xiaomei Zhang, Yanjun Zhang, Leo Yu Zhang, Chao Chen, Shengshan Hu, Asif Gill, Shirui Pan,
• Abstract summary: 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.
• Score: 51.336009662771396
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The Large Language Model (LLM) watermark is a newly emerging technique that shows promise in addressing concerns surrounding LLM copyright, monitoring AI-generated text, and preventing its misuse. The LLM watermark scheme commonly includes generating secret keys to partition the vocabulary into green and red lists, applying a perturbation to the logits of tokens in the green list to increase their sampling likelihood, thus facilitating watermark detection to identify AI-generated text if the proportion of green tokens exceeds a threshold. However, recent research indicates that watermarking methods using numerous keys are susceptible to removal attacks, such as token editing, synonym substitution, and paraphrasing, with robustness declining as the number of keys increases. Therefore, the state-of-the-art watermark schemes that employ fewer or single keys have been demonstrated to be more robust against text editing and paraphrasing. In this paper, we propose a novel green list stealing attack against the state-of-the-art LLM watermark scheme and systematically examine its vulnerability to this attack. We formalize the attack as a mixed integer programming problem with constraints. We evaluate our attack under a comprehensive threat model, including an extreme scenario where the attacker has no prior knowledge, lacks access to the watermark detector API, and possesses no information about the LLM's parameter settings or watermark injection/detection scheme. Extensive experiments on LLMs, such as OPT and LLaMA, demonstrate that our attack can successfully steal the green list and remove the watermark across all settings.

Related papers

• 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)
• Topic-Based Watermarks for LLM-Generated Text [46.71493672772134]
  This paper proposes a novel topic-based watermarking algorithm for large language models (LLMs) By using topic-specific token biases, we embed a topic-sensitive watermarking into the generated text. We demonstrate that our proposed watermarking scheme classifies various watermarked text topics with 99.99% confidence.
  arXiv  Detail & Related papers  (2024-04-02T17:49:40Z)
• Bypassing LLM Watermarks with Color-Aware Substitutions [11.724935807582513]
  Self Color Testing-based Substitution (SCTS) is the first color-aware'' attack. SCTS successfully evades watermark detection using fewer number of edits than related work. We show both theoretically and empirically that SCTS can remove the watermark for arbitrarily long watermarked text.
  arXiv  Detail & Related papers  (2024-03-19T17:54:39Z)
• Watermark Stealing in Large Language Models [2.1165011830664673]
  We show that querying the API of the watermarked LLM to approximately reverse-engineer a watermark enables practical spoofing attacks. We are the first to propose an automated WS algorithm and use it in the first comprehensive study of spoofing and scrubbing in realistic settings.
  arXiv  Detail & Related papers  (2024-02-29T17:12:39Z)
• Adaptive Text Watermark for Large Language Models [8.100123266517299]
  It is challenging to generate high-quality watermarked text while maintaining strong security, robustness, and the ability to detect watermarks without prior knowledge of the prompt or model. This paper proposes an adaptive watermarking strategy to address this problem.
  arXiv  Detail & Related papers  (2024-01-25T03:57:12Z)
• 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)
• 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.