Continuous Authentication Using One-class Classifiers and their Fusion

TL;DR

This paper investigates using only genuine user samples with one-class classifiers for continuous authentication, showing they can perform comparably to multi-class classifiers when sufficient genuine data is available.

Contribution

It demonstrates the effectiveness of four one-class classifiers and their fusion for continuous authentication without impostor data, a novel approach in this context.

Findings

OCC and their fusion can match MCC performance with enough genuine data.

OCC-based CAS do not require impostor samples during enrollment.

Fusion of OCC improves authentication accuracy.

Abstract

While developing continuous authentication systems (CAS), we generally assume that samples from both genuine and impostor classes are readily available. However, the assumption may not be true in certain circumstances. Therefore, we explore the possibility of implementing CAS using only genuine samples. Specifically, we investigate the usefulness of four one-class classifiers OCC (elliptic envelope, isolation forest, local outliers factor, and one-class support vector machines) and their fusion. The performance of these classifiers was evaluated on four distinct behavioral biometric datasets, and compared with eight multi-class classifiers (MCC). The results demonstrate that if we have sufficient training data from the genuine user the OCC, and their fusion can closely match the performance of the majority of MCC. Our findings encourage the research community to use OCC in order to build CAS as they do not require knowledge of impostor class during the enrollment process.