A Principled Approach to Natural Language Watermarking
Recently, there has been a surge in machine-generated natural language content being misused by unauthorized parties. Watermarking is a well-recognized technique to address the issue by tracing the provenance of the text. However, we found that most existing watermarking systems for texts are subject to ad hoc design and thus suffer from fundamental vulnerabilities.
Authors
- Liyao Xiang (ORCID: https://orcid.org/0000-0003-0165-4930)
- Xinbing Wang (ORCID: https://orcid.org/0000-0002-0357-8356)
- Zhe Ji (ORCID: https://orcid.org/0009-0005-8803-1737)
- Yan Zheng (ORCID: https://orcid.org/0000-0001-6734-341X)
- Qiansiqi Hu
Institutions
- Shanghai Jiao Tong University (CN)
Publication Details
- Published
- 2024-10-26
- DOI
- https://doi.org/10.1145/3664647.3681544
- Citations
- 4
- Primary Topic
- Advanced Steganography and Watermarking Techniques
- Type
- article
- Field-Weighted Citation Impact
- 1.00