Privacy-preserving Neural Representations of Text

TL;DR

This paper investigates privacy risks in neural NLP models by analyzing how hidden representations can leak private information and proposes defense strategies to enhance privacy without significantly sacrificing utility.

Contribution

It introduces a framework for measuring privacy leakage from neural representations and proposes novel training methods to defend against such attacks.

Findings

Modified training objectives improve privacy of neural representations.

Tradeoff between privacy and utility is characterized.

Defense methods increase privacy without major utility loss.

Abstract

This article deals with adversarial attacks towards deep learning systems for Natural Language Processing (NLP), in the context of privacy protection. We study a specific type of attack: an attacker eavesdrops on the hidden representations of a neural text classifier and tries to recover information about the input text. Such scenario may arise in situations when the computation of a neural network is shared across multiple devices, e.g. some hidden representation is computed by a user's device and sent to a cloud-based model. We measure the privacy of a hidden representation by the ability of an attacker to predict accurately specific private information from it and characterize the tradeoff between the privacy and the utility of neural representations. Finally, we propose several defense methods based on modified training objectives and show that they improve the privacy of neural representations.