An Unforgeable Publicly Verifiable Watermark for Large Language Models

arXiv:2307.16230v5 Announce Type: replace
Abstract: Recently, text watermarking algorithms for large language models (LLMs) have been proposed to mitigate the potential harms of text generated by LLMs, including fake news and copyright issues. However, current watermark detection algorithms require the secret key used in the watermark generation process, making them susceptible to security breaches and counterfeiting during public detection. To address this limitation, we propose an unforgeable publicly verifiable watermark algorithm that uses two different neural networks for watermark generation …

arxiv cs.cl language language models large language large language models type watermark