You Are How You Walk: Quantifying Privacy Risks in Step Count Data

TL;DR

This paper systematically investigates privacy risks associated with step count data from wearable devices, demonstrating potential attribute inference and linkability attacks through extensive real-world evaluations.

Contribution

It introduces the first systematic analysis of privacy risks in step count data, proposing two novel attacks and evaluating their effectiveness on real datasets.

Findings

Attribute inference attacks can accurately predict gender, age, and education.

Temporal linkability attacks reveal users' identity with high success.

Privacy risks in step count data are significant and warrant protective measures.

Abstract

Wearable devices have gained huge popularity in today's world. These devices collect large-scale health data from their users, such as heart rate and step count data, that is privacy sensitive, however it has not yet received the necessary attention in the academia. In this paper, we perform the first systematic study on quantifying privacy risks stemming from step count data. In particular, we propose two attacks including attribute inference for gender, age and education and temporal linkability. We demonstrate the severity of the privacy attacks by performing extensive evaluation on a real life dataset and derive key insights. We believe our results can serve as a step stone for deriving a privacy-preserving ecosystem for wearable devices in the future.