English

Robust Multi-bit Natural Language Watermarking through Invariant Features

Computation and Language 2023-06-12 v2 Artificial Intelligence

Abstract

Recent years have witnessed a proliferation of valuable original natural language contents found in subscription-based media outlets, web novel platforms, and outputs of large language models. However, these contents are susceptible to illegal piracy and potential misuse without proper security measures. This calls for a secure watermarking system to guarantee copyright protection through leakage tracing or ownership identification. To effectively combat piracy and protect copyrights, a multi-bit watermarking framework should be able to embed adequate bits of information and extract the watermarks in a robust manner despite possible corruption. In this work, we explore ways to advance both payload and robustness by following a well-known proposition from image watermarking and identify features in natural language that are invariant to minor corruption. Through a systematic analysis of the possible sources of errors, we further propose a corruption-resistant infill model. Our full method improves upon the previous work on robustness by +16.8% point on average on four datasets, three corruption types, and two corruption ratios. Code available at https://github.com/bangawayoo/nlp-watermarking.

Keywords

Cite

@article{arxiv.2305.01904,
  title  = {Robust Multi-bit Natural Language Watermarking through Invariant Features},
  author = {KiYoon Yoo and Wonhyuk Ahn and Jiho Jang and Nojun Kwak},
  journal= {arXiv preprint arXiv:2305.01904},
  year   = {2023}
}

Comments

ACL 2023 long

R2 v1 2026-06-28T10:24:10.965Z