Semantics-Preserved Distortion for Personal Privacy Protection in Information Management

TL;DR

This paper introduces a linguistically-grounded text distortion method that preserves semantics while protecting personal privacy in NLP tasks, demonstrating effectiveness across multiple applications and attack scenarios.

Contribution

It proposes a novel Neighboring Distribution Divergence metric and two frameworks for semantic-preserving text distortion, advancing privacy protection techniques in NLP.

Findings

Effective in named entity recognition, constituency parsing, and machine reading comprehension.

Outperforms structural approaches in attribute attack resistance.

Limits sensitive data memorization in medical information management.

Abstract

In recent years, machine learning - particularly deep learning - has significantly impacted the field of information management. While several strategies have been proposed to restrict models from learning and memorizing sensitive information from raw texts, this paper suggests a more linguistically-grounded approach to distort texts while maintaining semantic integrity. To this end, we leverage Neighboring Distribution Divergence, a novel metric to assess the preservation of semantic meaning during distortion. Building on this metric, we present two distinct frameworks for semantic-preserving distortion: a generative approach and a substitutive approach. Our evaluations across various tasks, including named entity recognition, constituency parsing, and machine reading comprehension, affirm the plausibility and efficacy of our distortion technique in personal privacy protection. We also test our method against attribute attacks in three privacy-focused assignments within the NLP domain, and the findings underscore the simplicity and efficacy of our data-based improvement approach over structural improvement approaches. Moreover, we explore privacy protection in a specific medical information management scenario, showing our method effectively limits sensitive data memorization, underscoring its practicality.