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

arXiv: https://arxiv.org/abs/2501.02441 · HTML: https://mlsanity.com/paper/2501.02441/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 5 Jan 2025.

## Builds on (most cited first, 19 of 19)

- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [Provable Robust Watermarking for AI-Generated Text](https://mlsanity.com/paper/2306.17439/) (2023)
- [Undetectable Watermarks for Language Models](https://mlsanity.com/paper/2306.09194/) (2023)
- [Unbiased Watermark for Large Language Models](https://mlsanity.com/paper/2310.10669/) (2023)
- [Protecting Language Generation Models via Invisible Watermarking](https://mlsanity.com/paper/2302.03162/) (2023)
- [Testing of Detection Tools for AI-Generated Text](https://mlsanity.com/paper/2306.15666/) (2023)
- [Three Bricks to Consolidate Watermarks for Large Language Models](https://mlsanity.com/paper/2308.00113/) (2023)
- [Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models](https://mlsanity.com/paper/2305.15594/) (2023)
- [Evading Watermark based Detection of AI-Generated Content](https://mlsanity.com/paper/2305.03807/) (2023)
- [Watermarking Text Generated by Black-Box Language Models](https://mlsanity.com/paper/2305.08883/) (2023)
- [Mark My Words: Analyzing and Evaluating Language Model Watermarks](https://mlsanity.com/paper/2312.00273/) (2023)
- [A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules](https://mlsanity.com/paper/2404.01245/) (2024)
- [Unveiling Security, Privacy, and Ethical Concerns of ChatGPT](https://mlsanity.com/paper/2307.14192/) (2023)
- [A Systematic Review on Model Watermarking for Neural Networks](https://mlsanity.com/paper/2009.12153/) (2020)
- [Copyright Protection in Generative AI: A Technical Perspective](https://mlsanity.com/paper/2402.02333/) (2024)
- [Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs](https://mlsanity.com/paper/2402.05864/) (2024)
- [Score Attack: A Lower Bound Technique for Optimal Differentially Private Learning](https://mlsanity.com/paper/2303.07152/) (2023)
- [Towards Better Statistical Understanding of Watermarking LLMs](https://mlsanity.com/paper/2403.13027/) (2024)

## Built on by (most cited first, 2 of 2)

- [AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees](https://mlsanity.com/paper/2510.01268/) (2025)
- [Do Large Language Models (Really) Need Statistical Foundations?](https://mlsanity.com/paper/2505.19145/) (2025)

## Abstract (arXiv)

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 distillation and inclusion of copyrighted materials in their training data without proper attribution or licensing, an issue that falls under the broader concern 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 the data generated by another LLM. 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 test statistics, determine optimal rejection thresholds, and explicitly control type I and type II errors. Furthermore, we establish the asymptotic optimality properties of the proposed tests, and demonstrate the empirical effectiveness through intensive numerical experiments.