A dexterous feature selection artificial immune system algorithm for keystroke dynamics. Issue 1 (2nd January 2016)

• Record Type: Journal Article
• Authors: Chandrasekar, V.; Suresh Kumar, S.
• Is Part Of: Stochastic analysis and applications. Volume 34:Issue 1(2016)
• Page Start: 147
• Page End: 154
• Publication Date: 2016-01-02
• Subjects: Keystroke dynamics; behavioral biometric; feature selection; Hausdroff timing; 97PXX; 11K55; Stochastic analysis -- Periodicals; 519.2205
• DOI: 10.1080/07362994.2015.1110707
• Languages: English
• ISSNs: 0736-2994

Abstract

ABSTRACT: The main problem in security protecting the computer or resources from intruders. The password and username are the most common means to provide security. But this method has many loop holes such as password sharing, shoulder surfing, brute-force attack, dictionary attack, guessing, and many more. Keystroke dynamics is one popular and inexpensive behavioral biometric technology, which identifies the authenticity of a user when the user is working via a keyboard. Keystroke features like dwell time and flight time of every user are evaluated in this paper by preprocessing techniques such as Hausdroff timing, mean, median, and standard deviation. The artificial immune system is used for feature selection, and comparison between preprocessing techniques is shown.