ProPILE：探究大语言模型中的隐私泄露
ProPILE: Probing Privacy Leakage in Large Language Models
AI总结：
本文提出ProPILE探测工具，让数据主体通过基于自身PII构建提示来评估大语言模型中的隐私泄露风险，并在OPT-1.3B和Pile数据集上验证其有效性，为数据主体提供隐私意识与控制手段。
摘要：
大语言模型（LLMs）的快速发展和广泛使用引发了人们对个人身份信息（PII）潜在泄露的严重担忧。这些模型通常在海量网络收集的数据上进行训练，这些数据可能无意中包含了敏感的个人数据。本文提出了ProPILE，这是一种新颖的探测工具，旨在让数据主体（即PII的所有者）了解基于LLM的服务中潜在的PII泄露情况。ProPILE允许数据主体基于自己的PII构建提示，以评估LLM中的隐私侵入程度。我们展示了它在OPT-1.3B模型上的应用，该模型在公开可用的Pile数据集上进行了训练。我们展示了假设的数据主体如何评估其PII被包含在Pile数据集中并被泄露的可能性。LLM服务提供商也可以利用ProPILE，通过专门为其内部模型调优的更强大的提示，有效评估自身的PII泄露水平。该工具代表了朝着赋予数据主体对网络上自身数据的意识和控制权迈出的开创性一步。
英文摘要：
The rapid advancement and widespread use of large language models (LLMs) have raised significant concerns regarding the potential leakage of personally identifiable information (PII). These models are often trained on vast quantities of web-collected data, which may inadvertently include sensitive personal data. This paper presents ProPILE, a novel probing tool designed to empower data subjects, or the owners of the PII, with awareness of potential PII leakage in LLM-based services. ProPILE lets data subjects formulate prompts based on their own PII to evaluate the level of privacy intrusion in LLMs. We demonstrate its application on the OPT-1.3B model trained on the publicly available Pile dataset. We show how hypothetical data subjects may assess the likelihood of their PII being included in the Pile dataset being revealed. ProPILE can also be leveraged by LLM service providers to effectively evaluate their own levels of PII leakage with more powerful prompts specifically tuned for their in-house models. This tool represents a pioneering step towards empowering the data subjects for their awareness and control over their own data on the web.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
