A Statistical Hypothesis Testing Framework for Data Misappropriation Detection in Large Language Models

Abstract:   Large Language Models (LLMs) are rapidly gaining enormous popularity in recent years. However, the training of LLMs has raised significant privacy and legal concerns, particularly regarding the inclusion of copyrighted materials in their training data without proper attribution or licensing, which falls under the broader issue of data misappropriation. In this article, we focus on a specific problem of data misappropriation detection, namely, to determine whether a given LLM has incorporated data generated by another LLM. To address this issue, we propose embedding watermarks into the copyrighted training data and formulating the detection of data misappropriation as a hypothesis testing problem. We develop a general statistical testing framework, construct a pivotal statistic, determine the optimal rejection threshold, and explicitly control the type I and type II errors. Furthermore, we establish the asymptotic optimality properties of the proposed tests, and demonstrate its empirical effectiveness through intensive numerical experiments.

CV:   Linjun Zhang is an Associate Professor in the Department of Statistics, at Rutgers University. He obtained his Ph.D. in Statistics at the Wharton School, the University of Pennsylvania in 2019, and received J. Parker Bursk Memorial Prize and Donald S. Murray Prize for excellence in research and teaching, respectively upon graduation. He also received the NSF CAREER Award, and Rutgers Presidential Teaching Award in 2024. His current research interests include algorithmic fairness, privacy-preserving data analysis, deep learning theory, and high-dimensional statistics.