Efficiency Issues and Improving Implementation of Keystroke Biometric Systems

Efficiency Issues and Improving Implementation of Keystroke Biometric Systems

Ali Kartit (LTI Laboratory, ENSAJ, Chouaib Doukkali University, Morocco) and Farida Jaha (LTI Laboratory, ENSAJ, Chouaib Doukkali University, Morocco)
Copyright: © 2020 |Pages: 13
DOI: 10.4018/978-1-5225-9715-5.ch077

Abstract

Keystroke dynamics is a heavy field for researches; a lot of solutions have been proposed in this domain using different implementations usually based on Euclidean distance for measuring similarity between features vectors. However, the Euclidean distance method has a higher error equal rate compared with other classification methods, which makes the method less effective. Therefore, in the article, the authors propose their version of keystroke dynamics implementation based on K-NN, F-NN, and Manhattan distance as classifiers to improve the authentication efficiency. The flight times and dwell time between keys are used in this study.
Chapter Preview
Top

Background

Keystroke dynamics was and remains a strong field for research, the first documented research published by Forsen, Nelson and Staron (1977) dated back to 1977. Later, many other papers were appeared. For instance, Patil and Renke (2016) published a paper where they better cleared up keystroke dynamics, they mentioned some drawback of this biometric method and they distinguished two different keystroke dynamics authentications: static and continuous. In static, the user is asked to type his login and password, then he is validated by comparing those data with his pre-calculated profile. In the continuous authentication, the end-user’s biometric data is captured throughout the use of the system. The use of the second kind of authentication prevents an impostor from taking control of the machine when its legal user is absent (several users leave their workstations without locking them or putting them in sleep mode). In this case keystroke recognition can be used as a behavioral intrusion detection system. Grant Pannell and Helen Ashman (2010) combined a set of factors including CPU usage, sites visited and keystroke biometric to implement a behavioral IDS to detect unauthorized users through their system usage. On the same page, Avasthi and Sanwal (2016) gave the existing approaches, security and challenges of keystroke dynamics in order to motivate the researches to further come with more innovative improvements. Some other researchers like Panasiuk, Dabrowski, Saeed, and Bochenska-Wlostowska (2014) devoted their studies to compare different keystroke dynamics databases and to test if the same algorithm running on two theoretically identical databases gives the same results.

Other research tried to improve the EER (Error Equal Rate) and the security level of the devices using keystroke biometric like Morales, Falanga, Fierrez, Sansone, and OrtegaGarcia (2015) team and Nagargoje, Lomte, Auti, and Rokade (2014) team who combined keystroke and mouse movement to authenticate the user and increase the device confidentiality.

Complete Chapter List

Search this Book:
Reset