Watermarking Text Data on Large Language Models for Dataset Copyright Protection.
Yixin LiuHongsheng HuXuyun ZhangLichao SunPublished in: CoRR (2023)
Keyphrases
- copyright protection
- language model
- text data
- text mining
- digital watermarking
- robust watermarking
- watermarking scheme
- digital images
- text classification
- image watermarking
- watermarking algorithm
- multimedia content
- n gram
- high dimensional
- structured data
- probabilistic model
- text documents
- watermarking technique
- information retrieval
- high dimensional data
- image authentication
- multimedia data
- document collections
- watermarking method
- query expansion
- data sets
- watermark embedding
- machine learning
- image processing
- data sources
- information extraction