PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiao, Yijia, Jin, Yiqiao, Bai, Yushi, Wu, Yue, Yang, Xianjun, Luo, Xiao, Yu, Wenchao, Zhao, Xujiang, Liu, Yanchi, Gu, Quanquan, Chen, Haifeng, Wang, Wei, Cheng, Wei
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929561503006720
author Xiao, Yijia
Jin, Yiqiao
Bai, Yushi
Wu, Yue
Yang, Xianjun
Luo, Xiao
Yu, Wenchao
Zhao, Xujiang
Liu, Yanchi
Gu, Quanquan
Chen, Haifeng
Wang, Wei
Cheng, Wei
author_facet Xiao, Yijia
Jin, Yiqiao
Bai, Yushi
Wu, Yue
Yang, Xianjun
Luo, Xiao
Yu, Wenchao
Zhao, Xujiang
Liu, Yanchi
Gu, Quanquan
Chen, Haifeng
Wang, Wei
Cheng, Wei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2310_02469
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners
Xiao, Yijia
Jin, Yiqiao
Bai, Yushi
Wu, Yue
Yang, Xianjun
Luo, Xiao
Yu, Wenchao
Zhao, Xujiang
Liu, Yanchi
Gu, Quanquan
Chen, Haifeng
Wang, Wei
Cheng, Wei
Computation and Language
Artificial Intelligence
Machine Learning
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.
title PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2310.02469