Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations

作者：Oluwaseyi Feyisetan, Borja Balle, Thomas Drake, Tom Diethe · 发表于：Web Search and Data Mining · 年份：2019 · DOI：10.1145/3336191.3371856 · 被引用次数：234 · 研究领域：Computer Science、Mathematics

Accurately learning from user data while providing quantifiable privacy guarantees provides an opportunity to build better ML models while maintaining user trust. This paper presents a formal approach to carrying out privacy preserving text perturbation using the notion of d_χ-privacy designed to achieve geo-indistinguishability in location data. Our approach applies carefully calibrated noise to vector representation of words in a high dimension space as defined by word embedding models. We present a privacy proof that satisfies d_χ-privacy where the privacy parameter $\varepsilon$ provides guarantees with respect to a distance metric defined by the word embedding space. We demonstrate how $\varepsilon$ can be selected by analyzing plausible deniability statistics backed up by large scale analysis on GloVe and fastText embeddings. We conduct privacy audit experiments against $2$ baseline models and utility experiments on 3 datasets to demonstrate the tradeoff between privacy and utility for varying values of varepsilon on different task types. Our results demonstrate practical utility (< 2% utility loss for training binary classifiers) while providing better privacy guarantees than baseline models.