Deep Private-Feature Extraction

TL;DR

Deep Private-Feature Extractor (DPFE) is a deep learning model that uses information theoretic constraints to extract useful features while protecting sensitive information, balancing accuracy and privacy on resource-limited devices.

Contribution

The paper introduces DPFE, a novel model that employs information theoretic measures to enhance privacy in feature extraction, with practical evaluation on smartphones.

Findings

DPFE effectively balances accuracy and privacy in image tasks.

It maintains high primary task accuracy under moderate resource use.

DPFE's privacy preservation is validated using the new log-rank privacy measure.

Abstract

We present and evaluate Deep Private-Feature Extractor (DPFE), a deep model which is trained and evaluated based on information theoretic constraints. Using the selective exchange of information between a user's device and a service provider, DPFE enables the user to prevent certain sensitive information from being shared with a service provider, while allowing them to extract approved information using their model. We introduce and utilize the log-rank privacy, a novel measure to assess the effectiveness of DPFE in removing sensitive information and compare different models based on their accuracy-privacy tradeoff. We then implement and evaluate the performance of DPFE on smartphones to understand its complexity, resource demands, and efficiency tradeoffs. Our results on benchmark image datasets demonstrate that under moderate resource utilization, DPFE can achieve high accuracy for primary tasks while preserving the privacy of sensitive features.