Research Challenges in Designing Differentially Private Text Generation Mechanisms

TL;DR

This paper discusses the challenges in designing differentially private text generation mechanisms and proposes new frameworks to improve the privacy-utility tradeoff in NLP models.

Contribution

It introduces the LAC framework and three local noise calibration techniques to enhance differential privacy in text generation.

Findings

Identifies limitations of fixed global sensitivity in current mechanisms.

Proposes a privacy amplification step to improve utility.

Suggests local region-based noise calibration methods.

Abstract

Accurately learning from user data while ensuring quantifiable privacy guarantees provides an opportunity to build better Machine Learning (ML) models while maintaining user trust. Recent literature has demonstrated the applicability of a generalized form of Differential Privacy to provide guarantees over text queries. Such mechanisms add privacy preserving noise to vectorial representations of text in high dimension and return a text based projection of the noisy vectors. However, these mechanisms are sub-optimal in their trade-off between privacy and utility. This is due to factors such as a fixed global sensitivity which leads to too much noise added in dense spaces while simultaneously guaranteeing protection for sensitive outliers. In this proposal paper, we describe some challenges in balancing the tradeoff between privacy and utility for these differentially private text mechanisms. At a high level, we provide two proposals: (1) a framework called LAC which defers some of the noise to a privacy amplification step and (2), an additional suite of three different techniques for calibrating the noise based on the local region around a word. Our objective in this paper is not to evaluate a single solution but to further the conversation on these challenges and chart pathways for building better mechanisms.