G.K.R. Lau, X. Niu., H. Dao, J. Chen, C.-S. Foo and B.K.H. Low (2024). Framework for Robust and Scalable Text Watermarking. The 2024 Conference on Empirical Methods in Natural Language Processing.
Abstract:
Protecting intellectual property (IP) of text such as articles and code is increasingly important, especially as sophisticated attacks become possible, such as paraphrasing by large language models (LLMs) or even unauthorized training of LLMs on copyrighted text to infringe such IP. However, existing text watermarking methods are not robust enough against such attacks nor scalable to millions of users for practical implementation. In this paper, we propose Waterfall, the first training-free framework for robust and scalable text watermarking applicable across multiple text types (e.g., articles, code) and languages supportable by LLMs, for general text and LLM data provenance. Waterfall comprises several key innovations, such as being the first to use LLM as paraphrasers for watermarking along with a novel combination of techniques that are surprisingly effective in achieving robust verifiability and scalability. We empirically demonstrate that Waterfall achieves significantly better scalability, robust verifiability, and computational efficiency compared to SOTA article-text watermarking methods, and also showed how it could be directly applied to the watermarking of code.
License type:
Attribution 4.0 International (CC BY 4.0)
Funding Info:
This research / project is supported by the National Research Foundation - AI Singapore Programme
Grant Reference no. : AISG2-PhD/2023-01- 039J
This research / project is supported by the National Research Foundation - Campus for Research Excellence and Technological Enterprise (CREATE) Programme
Grant Reference no. :
This research / project is supported by the National Research Foundation Singapore and the Singapore Ministry of Digital Development and Innovation, National AI Group - AI Visiting Professorship Programme
Grant Reference no. : AIVP-2024-001