ESN-SVM Hybrid Architecture for Free-Text Keystroke Authentication

Chavan, Nishant Premnath (2025) ESN-SVM Hybrid Architecture for Free-Text Keystroke Authentication. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (3MB) | Preview

Abstract

Keystroke Dynamics (KD) is a behavioural biometric method that identifies a user based on their typing pattern for authentication, providing non-intrusive and continuous authentication. In keystroke dynamics, each keystroke generates timing patterns that are important to identify a user, but current methods depend heavily on manually engineered features rather than core temporal features. Echo State Networks (ESNs) have temporal memory capabilities that can preserve natural user typing patterns without altering them. This study proposes a hybrid architecture consisting of ESNs for temporal pattern recognition in combination with Support Vector Machine (SVM) to make strong decision boundaries. This hybrid method addresses the main weaknesses of existing approaches which require large training datasets or struggle with different typing patterns. The results show that ESN, when combined with SVM, achieves excellent performance with an Equal Error Rate (EER) of 2.63%, which surpasses the 5% research hypothesis threshold, while outperforming ESN baseline authentication by 82.7%. The system also achieves a false non match rate (FNMR) of 1.32% and a false match rate (FMR) of 2.63%, based on simulation, thus making it ready for practical implementation.

Item Type:	Thesis (Masters)
Supervisors:	Name Email McCabe, Liam UNSPECIFIED
Uncontrolled Keywords:	Keystroke Dynamics; Echo State Network; Support Vector Machine; Biometric Authentication
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Biometric Identification Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Ciara O'Brien
Date Deposited:	15 Jun 2026 12:49
Last Modified:	15 Jun 2026 12:49
URI:	https://norma.ncirl.ie/id/eprint/9349

Actions (login required)

View Item