Large Language Models Can Be Good Privacy Protection Learners

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

Keywords: Large language model, Privacy protection

TL;DR: We introduce PPLM (Privacy Protection Fine-Tuning for LLM), which emphasizes instruction-based tuning with positive and negative examples, enabling LLMs to assimilate knowledge while preserving privacy.

Abstract:

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 sensitive personally identifiable information (PII). Direct fine-tuning LLMs on this data without privacy protection poses a risk of leakage.
To address this challenge, we introduce Privacy Protection Language Models (PPLM), a novel paradigm for fine-tuning LLMs that effectively injects domain-specific knowledge while safeguarding data privacy.
Our work offers a theoretical analysis for model design and delves into various techniques such as corpus curation, penalty-based unlikelihood in training loss, and 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 privacy protection learners.

Primary Area: societal considerations including fairness, safety, privacy

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 4924