Fast Free-text Authentication via Instance-based Keystroke Dynamics

TL;DR

This paper introduces a novel graph comparison algorithm called ITAD that significantly reduces the number of keystrokes needed for free-text user authentication, achieving state-of-the-art accuracy with fewer characters.

Contribution

The paper presents the ITAD metric and demonstrates its effectiveness in improving free-text keystroke authentication accuracy with fewer keystrokes than previous methods.

Findings

Achieves EER of 9.7% with 100 digraphs

Achieves EER of 7.8% with 200 digraphs

Outperforms previous state-of-the-art methods

Abstract

Keystroke dynamics study the way in which users input text via their keyboards. Having the ability to differentiate users, typing behaviors can unobtrusively form a component of a behavioral biometric recognition system to improve existing account security. Keystroke dynamics systems on free-text data have previously required 500 or more characters to achieve reasonable performance. In this paper, we propose a novel instance-based graph comparison algorithm called the instance-based tail area density (ITAD) metric to reduce the number of keystrokes required to authenticate users. Additionally, commonly used features in the keystroke dynamics literature, such as monographs and digraphs, are all found to be useful in informing who is typing. The usefulness of these features for authentication is determined using a random forest classifier and validated across two publicly available datasets. Scores from the individual features are fused to form a single matching score. With the fused matching score and our ITAD metric, we achieve equal error rates (EERs) for 100 and 200 testing digraphs of 9.7% and 7.8% for the Clarkson II dataset, improving upon state-of-the-art of 35.3% and 15.3%.