PhysioGait: Context-Aware Physiological Context Modeling for Person Re-identification Attack on Wearable Sensing

TL;DR

This paper introduces PhysioGait, a novel model that leverages physiological and physical biometric signals to re-identify individuals from wearable sensing data, highlighting privacy risks in healthcare data sharing.

Contribution

PhysioGait is the first context-aware physiological signal model using a Multi-Modal Siamese CNN for person re-identification in wearable data.

Findings

Achieved 89%-93% re-identification accuracy on real datasets.

Demonstrated privacy risks in publicly shared wearable sensing data.

Validated model effectiveness across multiple datasets.

Abstract

Person re-identification is a critical privacy breach in publicly shared healthcare data. We investigate the possibility of a new type of privacy threat on publicly shared privacy insensitive large scale wearable sensing data. In this paper, we investigate user specific biometric signatures in terms of two contextual biometric traits, physiological (photoplethysmography and electrodermal activity) and physical (accelerometer) contexts. In this regard, we propose PhysioGait, a context-aware physiological signal model that consists of a Multi-Modal Siamese Convolutional Neural Network (mmSNN) which learns the spatial and temporal information individually and performs sensor fusion in a Siamese cost with the objective of predicting a person's identity. We evaluated PhysioGait attack model using 4 real-time collected datasets (3-data under IRB #HP-00064387 and one publicly available data) and two combined datasets achieving 89% - 93% accuracy of re-identifying persons.