TY - JOUR AU - Feyisetan, Oluwaseyi AU - Aggarwal, Abhinav AU - Xu, Zekun AU - Teissier, Nathanael PY - 2021/04/18 Y2 - 2024/03/28 TI - Research Challenges in Designing Differentially Private Text Generation Mechanisms JF - The International FLAIRS Conference Proceedings JA - FLAIRS VL - 34 IS - 0 SE - Special Track: Security, Privacy, Trust and Ethics in AI DO - 10.32473/flairs.v34i1.128461 UR - https://journals.flvc.org/FLAIRS/article/view/128461 SP - AB - <p class="p1">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.</p><p class="p1">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.</p> ER -