Differential Privacy in Natural Language Processing: The Story So Far

TL;DR

This paper reviews the application of Differential Privacy in NLP, discussing current challenges, vulnerabilities, and future directions for integrating privacy-preserving techniques into unstructured text data processing.

Contribution

It provides a comprehensive overview of how Differential Privacy is being adapted for NLP, highlighting existing research, challenges, and future research directions.

Findings

Differential Privacy can protect sensitive information in NLP tasks.

Current methods face challenges due to NLP's unstructured data nature.

Future research is needed to effectively implement Differential Privacy in NLP.

Abstract

As the tide of Big Data continues to influence the landscape of Natural Language Processing (NLP), the utilization of modern NLP methods has grounded itself in this data, in order to tackle a variety of text-based tasks. These methods without a doubt can include private or otherwise personally identifiable information. As such, the question of privacy in NLP has gained fervor in recent years, coinciding with the development of new Privacy-Enhancing Technologies (PETs). Among these PETs, Differential Privacy boasts several desirable qualities in the conversation surrounding data privacy. Naturally, the question becomes whether Differential Privacy is applicable in the largely unstructured realm of NLP. This topic has sparked novel research, which is unified in one basic goal: how can one adapt Differential Privacy to NLP methods? This paper aims to summarize the vulnerabilities addressed by Differential Privacy, the current thinking, and above all, the crucial next steps that must be considered.