精准定位长文本中被水印标记的片段，提升伪造文本检测能力
Efficiently Identifying Watermarked Segments in Mixed-Source Texts
- 基于几何覆盖原理，判断长文本是否存在水印段落
- 采用自适应在线学习算法，精确找出水印位置
- 支持多种水印技术，适合内容安全与学术审查场景
大型语言模型中的文本水印正被广泛用于识别合成文本，以应对假新闻和学术不端等问题。现有检测方法多聚焦于整篇文档是否含水印，却忽略了在混合来源长文本中定位具体水印片段的实际需求。受抄袭检测系统启发，本文提出两种新型局部水印检测方法：一是基于几何覆盖的检测框架，用于判断长文本中是否存在水印段落；二是自适应在线学习算法，可精确定位水印所在位置。在三种主流水印技术（KGW-Watermark、Unigram-Watermark、Gumbel-Watermark）上的实验表明，该方法准确率显著优于基线模型。此外，本框架具备良好可扩展性，适用于其他水印技术，为高精度水印定位提供了新思路。代码已开源：https://github.com/XuandongZhao/llm-watermark-location。
原文摘要 · Abstract (English)
Text watermarks in large language models (LLMs) are increasingly used to detect synthetic text, mitigating misuse cases like fake news and academic dishonesty. While existing watermarking detection techniques primarily focus on classifying entire documents as watermarked or not, they often neglect the common scenario of identifying individual watermark segments within longer, mixed-source documents. Drawing inspiration from plagiarism detection systems, 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. Evaluated on three popular watermarking techniques (KGW-Watermark, Unigram-Watermark, and Gumbel-Watermark), our approach achieves high accuracy, significantly outperforming baseline methods. Moreover, our framework is adaptable to other watermarking techniques, offering new insights for precise watermark detection. Our code is publicly available at https://github.com/XuandongZhao/llm-watermark-location
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。