Keystroke Dynamics Authentication based on Naïve Bayes Classifier

Abstract

Authentication is the process of determining whether someone or something is,
in fact, who or what it is declared to be. As the dependence upon computers and
computer networks grows, the need for user authentication has increased. User’s
claimed identity can be verified by one of several methods. One of the most popular
of these methods is represented by (something user know), such as password or
Personal Identification Number (PIN). Biometrics is the science and technology of
authentication by identifying the living individual’s physiological or behavioral
attributes. Keystroke authentication is a new behavioral access control system to
identify legitimate users via their typing behavior. The objective of this paper is to
provide user authentication based on keystroke dynamic in order to avoid un
authorized user access to the system. Naive Bayes Classifier (NBC) is applied for
keystroke authentication using unigraph and diagraph keystroke features. The
unigraph Dwell Time (DT), diagraph Down-Down Time (DDT) features, and
combination of (DT and DDT) are used. The results show that the combination of
features (DT and DDT) produces better results with low error rate as compared
with using DT or DDT alone.