Does Your Phone Know Your Touch?
This work addresses security and authentication problems for mobile device users, but it is incremental as it applies existing methods to new biometric data.
The paper tackles continuous anomaly detection from biometric touch screen data by testing supervised learning methods on touch and swipe gestures, achieving over 95% accuracy for true negative and true positive scores across all gesture types, with logistic regression performing best.
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.