Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
Year: 2024
Type: preprint
Abstract: Large Language Models (LLMs) have demonstrated impressive capabilities in generating diverse and contextually rich text. However, concerns regarding copyright infringement arise as LLMs may inadvertently produce copyrighted material. In this paper, we first investigate the effectiveness of watermarking LLMs as a deterrent against the generation of copyrighted texts. Through theoretical analysis and empirical evaluation, we demonstrate that incorporating watermarks into LLMs significantly reduces the likelihood of generating copyrighted content, thereby addressing a critical concern in the deployment of LLMs. However, we also find that watermarking can have unintended consequences on Membership Inference Attacks (MIAs), which aim to discern whether a sample was part of the pretraining dataset and may be used to detect copyright violations. Surprisingly, we find that watermarking adversely affects the success rate of MIAs, complicating the task of detecting copyrighted text in the pretraining dataset. These results reveal the complex interplay between different regulatory measures, which may impact each other in unforeseen ways. Finally, we propose an adaptive technique to improve the success rate of a recent MIA under watermarking. Our findings underscore the importance of developing adaptive methods to study critical problems in LLMs with potential legal implications.
Source: arXiv (Cornell University)
Authors: Panaitescu-Liess, Michael-Andrei, Che, Zora, An, Bang, Xu, Yuancheng, Pathmanathan, Pankayaraj, Chakraborty, Souradip, Zhu, Sicheng, Goldstein, Tom, Huang, Furong
Institution: University of Maryland, College Park
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6929345765