100元2小时不限次数电话号码,全国空降200元快餐联系方式,24小时微信快餐妹,全国同城约资源匹配系统

科学研究
学术报告
当前位置: 学院主页 > 科学研究 > 学术报告 > 正文

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

发布时间：2025-06-18 作者： 浏览次数：
Speaker: 张林俊 DateTime: 6月20日（周五）上午10：00 - 11：00
Brief Introduction to Speaker:

张林俊教授，美国罗格斯大学


 Place: 新文科楼403会议室
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 empir...
主站蜘蛛池模板： 葫芦岛市| 石嘴山市| 都兰县| 阿合奇县| 石阡县| 施秉县| 荔浦县| 新疆| 什邡市| 永兴县| 台中县| 鸡东县| 荣昌县| 习水县| 东阳市| 柳河县| 江达县| 元江| 涿鹿县| 天水市| 中牟县| 商都县| 福清市| 茶陵县| 宜春市| 武义县| 拉萨市| 天等县| 抚远县| 庐江县| 弋阳县| 磴口县| 阳东县| 酉阳| 南开区| 梁平县| 抚远县| 南平市| 巴彦淖尔市| 专栏| 桃园市|