arXiv 2310.024692024-10-28cs.CLcs.AIcs.LG

PrivacyMind：大语言模型可成为情境化隐私保护学习者

PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners

University of California, Los Angeles（加州大学洛杉矶分校）；Georgia Institute of Technology（佐治亚理工学院）；Tsinghua University（清华大学）；University of California, Santa Barbara（加州大学圣巴巴拉分校）；NEC Laboratories America（美国NEC实验室）

Yijia Xiao, Yiqiao Jin, Yushi Bai, Yue Wu, Xianjun Yang, Xiao Luo, Wenchao Yu, Xujiang Zhao, Yanchi Liu, Quanquan Gu, Haifeng Chen, Wei Wang, Wei Cheng

备注：: Accepted at EMNLP 2024 Main

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对领域微调数据中的敏感 PII 泄露问题，提出 PrivacyMind 范式，通过理论分析与多种技术基准测试，证明正负例指令微调可在注入领域知识的同时保护推理隐私。

摘要：

大语言模型（LLM）的普及激发了人们利用特定领域数据对其进行微调以构建专用语言模型的浓厚兴趣。然而，此类特定领域微调数据通常包含情境敏感的个人身份信息（PII）。在没有隐私保护的情况下直接使用这些数据微调 LLM，会在推理阶段带来敏感 PII 数据泄露的风险。为应对这一挑战，我们提出了情境化隐私保护语言模型（Contextual Privacy Protection Language Models，PrivacyMind），这是一种用于微调 LLM 的新范式，能够在有效注入特定领域知识的同时保护推理时的数据隐私。我们的工作为模型设计提供了理论分析，并对语料库筛选、训练损失中基于惩罚的非似然方法、基于指令的微调等多种技术进行了基准测试。在不同数据集和场景下开展的大量实验证明了我们方法的有效性。尤其值得注意的是，同时使用正例和负例的指令微调作为一种颇具前景的方法脱颖而出，能够在增强模型知识的同时有效保护隐私数据。我们的工作凸显了大语言模型作为可靠的情境化隐私保护学习者的潜力。本工作的完整代码和数据可在 https://github.com/Yijia-Xiao/PrivacyMind 获取。

英文摘要：

The proliferation of Large Language Models (LLMs) has driven considerable interest in fine-tuning them with domain-specific data to create specialized language models. Nevertheless, such domain-specific fine-tuning data often contains contextually sensitive personally identifiable information (PII). Direct fine-tuning of LLMs on this data without privacy protection poses a risk of data leakage of sensitive PII during inference time. To address this challenge, we introduce Contextual Privacy Protection Language Models (PrivacyMind), a novel paradigm for fine-tuning LLMs that effectively injects domain-specific knowledge while safeguarding inference-time data privacy. Our work offers a theoretical analysis for model design and benchmarks various techniques such as corpus curation, penalty-based unlikelihood in training loss, instruction-based tuning, etc. Extensive experiments across diverse datasets and scenarios demonstrate the effectiveness of our approaches. In particular, instruction tuning with both positive and negative examples stands out as a promising method, effectively protecting private data while enhancing the model's knowledge. Our work underscores the potential for Large Language Models as robust contextual privacy protection learners. The complete code and data for the work can be found at https://github.com/Yijia-Xiao/PrivacyMind.

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。