The BeiHang Keystroke Dynamics Authentication System

TL;DR

This paper presents a comprehensive keystroke dynamics authentication system with an embedded device, online platform, new datasets, feature extraction method, and benchmark comparisons of classification algorithms.

Contribution

It introduces an embedded device and online system for keystroke authentication, along with new datasets and benchmark results for multiple classifiers.

Findings

Gabor filter bank effectively characterizes keystroke dynamics

Benchmark results for SVM, Gaussian, and nearest neighbor classifiers

Public databases promote keystroke authentication research

Abstract

Keystroke Dynamics is an important biometric solution for person authentication. Based upon keystroke dynamics, this paper designs an embedded password protection device, develops an online system, collects two public databases for promoting the research on keystroke authentication, exploits the Gabor filter bank to characterize keystroke dynamics, and provides benchmark results of three popular classification algorithms, one-class support vector machine, Gaussian classifier, and nearest neighbour classifier.