SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1910.08902 · 2019

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

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 dx-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 dx-privacy where the privacy parameter epsilon provides guarantees with respect to a distance metric defined by the word embedding space. We demonstrate how epsilon 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 epsilon on different task types. Our results demonstrate practical utility (< 2% utility loss for training binary classifiers) while providing better privacy guarantees than baseline models.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1910.08902")
get_code_for_paper("1910.08902")
have("1910.08902")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1910.08902.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1910.08902.svg)](https://syntology.ai/paper/1910.08902)

Connect an agent — have() is free.