网络与信息安全学报2026，Vol.12Issue(4)：62-75,14.DOI:10.11959/j.issn.2096-109x.AQ26114
面向大语言模型的鲁棒多比特水印算法
Robust multi-bit watermarking algorithm for large language models
摘要
Abstract
With the rapid development of large language models(LLM),text watermarking techniques that embed identifiable information into LLM-generated content have gradually become a hot research topic.Existing methods typically rely on the preceding token to generate a random seed,and use a pseudorandom approach to determine watermark embedding positions and partition the vocabulary,enabling watermark injection.Despite the achieved progress,existing methods still exhibit limited robustness against various text attacks,such as synonym substitution attacks.To this end,a semantic-oriented robust multi-bit watermarking(SRMW)algorithm was proposed.Specifi-cally,a pre-trained embedding model was employed to extract semantic representations of text.Then,different from existing methods that rely on local word-level information to generate random seeds,a semantic-driven water-mark projection model(WPM)was designed to construct random seeds based on text semantic representations,thereby pseudo-randomly determining watermark embedding positions and vocabulary partitioning strategies.Fur-thermore,a reconstruction loss and semantic consistency loss were designed to ensure the generalizability and ro-bustness of the constructed random seeds.Extensive experiments on three LLMs and two datasets demonstrated that the proposed SRMW achieved superior robustness compared to existing methods under various attack sce-narios,including synonym substitution and word deletion.关键词
多比特水印/大语言模型/信息隐藏Key words
multi-bit watermarking/LLM/information hiding分类
信息技术与安全科学引用本文复制引用
周海林,李博,张琨,洪日昌..面向大语言模型的鲁棒多比特水印算法[J].网络与信息安全学报,2026,12(4):62-75,14.基金项目
中央高校基本科研专项资金(No.JZ2025HGTG0289,No.PA2025IISL0114)The Fundamental Research Funds for the Central Universities(No.JZ2025HGTG0289,No.PA2025IISL0114) （No.JZ2025HGTG0289,No.PA2025IISL0114）
