Adaptive Biometric Strategy using Doddington Zoo Classification of User’s Keystroke Dynamics

Abstract

Securing personal, professional and even official data is a very critical issue nowadays, giving that these informations are safeguarded in different devices (mobile, computer) and various accounts (social networks, e-mails). To protect them from unauthorized acess, users generally are asked to use passwords. But using only these authentication solutions is no longer efficient against hacker attacks. Keystroke dynamics is a biometric promising modality that guarantees the recognition of the user's characteristics; his typing manner on the keyboard. Regarding that the typing rythm of the user changes over time, adaptive biometric solutions help to take into consideration these variations. In this paper we classify user into multiple categories according to Doddonghton Zoo classification. Afterwards, we apply an adaptive strategy specific to each category of users. The achived experiments demonstrate that an update strategy specific to the user class has improved significantly the obtained performances.

User Dependent Template Update for Keystroke Dynamics Recognition

“…To illustrate the benefits of the consideration of 7 classes of the Doddington zoo in the proposed approach, we compared it to the same adaptation approach without biometric menagerie and with the consideration of only 3 classes conducted in [23], namely sheep, goats and lambs. As demonstrated in Tables II and III, the proposed approach show improved performances as it proposes an adaptive strategy that is the most appropriate to the user's specificities.…”

A Systematic Literature Review on Latest Keystroke Dynamics Based Models

“…Doddington zoo: This classification has been applied to classifying the user into multiple categories, and each category has been adapted by a specific adaptation strategy [314].…”

Double serial adaptation mechanism for keystroke dynamics authentication based on a single password

“…It may be common for all users (a passphrase), or it may be a user specific password. This is the most utilized category in the literature [15,19,20,21].…”

“…It was already demonstrated in [19,47,56,57] that updating the used thresholds would improve the system performance. An individual decision threshold T s+1 j of session (s + 1) is adapted by decreasing it with a coefficient calculated by the average of the mean vector of reference µ and the standard deviation of the standard deviation vector σ, as indicated in Equation ( 5).…”