User Authentication via Keystroke Dynamics: An Artificial Immune System Based Approach
Kenneth Revett · 2011
Keystroke dynamics is a behavioral biometric that is based on how a user enters their login details. In this study, a set of eight attributes were extracted during the course of entering login details. This collection of attributes was used to form a reference signature (a biometric identification record) for subsequent authentication requests. The algorithm for the authentication process entails the deployment of an artificial immune based approach. The approach uses self-reactivity to discriminate self from non-self from the enrollment data. During the classification task, the system relies on deploying a pool of non-self reactive antibodies to perform a very general classification task. The results of this study indicate that the error rate is less than 5% in many cases. combination has their keystroke dynamics extracted and then compared with the stored reference signature. If they are within a prescribed tolerance limit - the user is authenticated. If not - then the system can decide whether to lock up the workstation - or take some other suitable action. In this study, a preliminary investigation of the application of the artificial immune system (AIS) is applied as a means of performing the authentication process. The AIS derives its inspiration from biological immune systems, and seems to serve as a natural approach to user authentication generally. In intruder detection systems, the AIS approach has been deployed with some success to identify. It is a natural approach that is designed to distinguish self from non- self. In the case of intrusion detection, non-self is a foreign entity which is attempting to gain access to the computer resources. The immune system acts as a surveillance mechanism, constantly vigilant looking for entities that are not typical of the host environment. Likewise, with an application to keystroke dynamics, the AIS approach monitors the keystroke dynamics of the user in order to determine whether they belong to the host (equally suitable for both static and continuous authentication modes). To date, there is a dearth of publications in this domain. This paper presents an overview of our system, which implements many aspects of the AIS approach, along with some preliminary results. We start by presenting a brief perspective on keystroke dynamics and artificial immune systems.