REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models

arXiv:2310.12362v2 Announce Type: replace
Abstract: We present REMARK-LLM, a novel efficient, and robust watermarking framework designed for texts generated by large language models (LLMs). Synthesizing human-like content using LLMs necessitates vast computational resources and extensive datasets, encapsulating critical intellectual property (IP). However, the generated content is prone to malicious exploitation, including spamming and plagiarism. To address the challenges, REMARK-LLM proposes three new components: (i) a learning-based message encoding module to infuse binary signatures into LLM-generated texts; (ii) a reparameterization module …

arxiv computational critical cs.cl cs.cr datasets framework generated generative human intellectual property language language models large llm llms novel property resources texts vast watermarking