Robust Multi-bit Natural Language Watermarking through Invariant Features
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- Anthology ID:
- 2023.acl-long.117
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2092–2115
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.117
- DOI:
- 10.18653/v1/2023.acl-long.117
- Cite (ACL):
- KiYoon Yoo, Wonhyuk Ahn, Jiho Jang, and Nojun Kwak. 2023. Robust Multi-bit Natural Language Watermarking through Invariant Features. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2092–2115, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Robust Multi-bit Natural Language Watermarking through Invariant Features (Yoo et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/teach-a-man-to-fish/2023.acl-long.117.pdf