1-Diffractor: Efficient and Utility-Preserving Text Obfuscation Leveraging Word-Level Metric Differential Privacy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Meisenbacher, Stephen, Chevli, Maulik, Matthes, Florian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917656235343872
author Meisenbacher, Stephen
Chevli, Maulik
Matthes, Florian
author_facet Meisenbacher, Stephen
Chevli, Maulik
Matthes, Florian
contents The study of privacy-preserving Natural Language Processing (NLP) has gained rising attention in recent years. One promising avenue studies the integration of Differential Privacy in NLP, which has brought about innovative methods in a variety of application settings. Of particular note are $\textit{word-level Metric Local Differential Privacy (MLDP)}$ mechanisms, which work to obfuscate potentially sensitive input text by performing word-by-word $\textit{perturbations}$. Although these methods have shown promising results in empirical tests, there are two major drawbacks: (1) the inevitable loss of utility due to addition of noise, and (2) the computational expensiveness of running these mechanisms on high-dimensional word embeddings. In this work, we aim to address these challenges by proposing $\texttt{1-Diffractor}$, a new mechanism that boasts high speedups in comparison to previous mechanisms, while still demonstrating strong utility- and privacy-preserving capabilities. We evaluate $\texttt{1-Diffractor}$ for utility on several NLP tasks, for theoretical and task-based privacy, and for efficiency in terms of speed and memory. $\texttt{1-Diffractor}$ shows significant improvements in efficiency, while still maintaining competitive utility and privacy scores across all conducted comparative tests against previous MLDP mechanisms. Our code is made available at: https://github.com/sjmeis/Diffractor.
format Preprint
id arxiv_https___arxiv_org_abs_2405_01678
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle 1-Diffractor: Efficient and Utility-Preserving Text Obfuscation Leveraging Word-Level Metric Differential Privacy
Meisenbacher, Stephen
Chevli, Maulik
Matthes, Florian
Computation and Language
The study of privacy-preserving Natural Language Processing (NLP) has gained rising attention in recent years. One promising avenue studies the integration of Differential Privacy in NLP, which has brought about innovative methods in a variety of application settings. Of particular note are $\textit{word-level Metric Local Differential Privacy (MLDP)}$ mechanisms, which work to obfuscate potentially sensitive input text by performing word-by-word $\textit{perturbations}$. Although these methods have shown promising results in empirical tests, there are two major drawbacks: (1) the inevitable loss of utility due to addition of noise, and (2) the computational expensiveness of running these mechanisms on high-dimensional word embeddings. In this work, we aim to address these challenges by proposing $\texttt{1-Diffractor}$, a new mechanism that boasts high speedups in comparison to previous mechanisms, while still demonstrating strong utility- and privacy-preserving capabilities. We evaluate $\texttt{1-Diffractor}$ for utility on several NLP tasks, for theoretical and task-based privacy, and for efficiency in terms of speed and memory. $\texttt{1-Diffractor}$ shows significant improvements in efficiency, while still maintaining competitive utility and privacy scores across all conducted comparative tests against previous MLDP mechanisms. Our code is made available at: https://github.com/sjmeis/Diffractor.
title 1-Diffractor: Efficient and Utility-Preserving Text Obfuscation Leveraging Word-Level Metric Differential Privacy
topic Computation and Language
url https://arxiv.org/abs/2405.01678