Does Your Phone Know Your Touch?

TL;DR

This study investigates supervised machine learning techniques to detect anomalies in biometric touch screen data, achieving over 95% accuracy in identifying individual touch patterns, with logistic regression performing best.

Contribution

It introduces a supervised approach using SVM, logistic regression, and GMM for continuous biometric touch anomaly detection, highlighting logistic regression's superior performance.

Findings

Logistic regression outperformed other models in accuracy.

Achieved over 95% true positive and negative rates.

Capacitive sensor data effectively captures individual touch patterns.

Abstract

This paper explores supervised techniques for continuous anomaly detection from biometric touch screen data. A capacitive sensor array used to mimic a touch screen as used to collect touch and swipe gestures from participants. The gestures are recorded over fixed segments of time, with position and force measured for each gesture. Support Vector Machine, Logistic Regression, and Gaussian mixture models were tested to learn individual touch patterns. Test results showed true negative and true positive scores of over 95% accuracy for all gesture types, with logistic regression models far outperforming the other methods. A more expansive and varied data collection over longer periods of time is needed to determine pragmatic usage of these results.