Privacy and Utility Preserving Sensor-Data Transformations

TL;DR

This paper introduces data transformation techniques for wearable sensor data that effectively protect user privacy by preventing sensitive inferences and re-identification, while maintaining high utility for activity recognition tasks.

Contribution

It presents novel transformation mechanisms that significantly reduce privacy risks in sensor data sharing with minimal impact on utility.

Findings

Prevented sensitive activity inference with less than 5% accuracy loss

Reduced user re-identification accuracy to random guess levels

Maintained activity recognition accuracy comparable to original data

Abstract

Sensitive inferences and user re-identification are major threats to privacy when raw sensor data from wearable or portable devices are shared with cloud-assisted applications. To mitigate these threats, we propose mechanisms to transform sensor data before sharing them with applications running on users' devices. These transformations aim at eliminating patterns that can be used for user re-identification or for inferring potentially sensitive activities, while introducing a minor utility loss for the target application (or task). We show that, on gesture and activity recognition tasks, we can prevent inference of potentially sensitive activities while keeping the reduction in recognition accuracy of non-sensitive activities to less than 5 percentage points. We also show that we can reduce the accuracy of user re-identification and of the potential inference of gender to the level of a random guess, while keeping the accuracy of activity recognition comparable to that obtained on the original data.