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

arXiv:2310.12362v2 Announce Type: replace-cross
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 …

abstract arxiv computational cs.cl cs.cr datasets framework generated generative however human human-like intellectual property language language models large language large language models llm llms novel property resources robust type vast watermarking