Open AccessResearch Challenges in Designing Differentially Private Text Generation Mechanisms
Author(s) -
Oluwaseyi Feyisetan,
Abhinav Aggarwal,
Zhengyu Xu,
Nathanael Teissier
Publication year - 2021
Publication title -
proceedings of the ... international florida artificial intelligence research society conference
Language(s) - English
Resource type - Journals
eISSN - 2334-0762
pISSN - 2334-0754
DOI - 10.32473/flairs.v34i1.128461
Subject(s) - differential privacy , computer science , dimension (graph theory) , noise (video) , suite , private information retrieval , projection (relational algebra) , conversation , theoretical computer science , data mining , data science , computer security , artificial intelligence , algorithm , mathematics , history , linguistics , philosophy , archaeology , image (mathematics) , pure mathematics
Accurately learning from user data while ensuring quantifiable privacy guarantees provides an opportunity to build better 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.
In this proposal paper, we describe some challenges in balancing this trade-off. 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.