A methodology for improving computer access security

• Published in: Computers & security Vol. 12; no. 7; pp. 657 - 662
• Main Author: Obaidat, M.S.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Ltd 1993; Elsevier Sequoia S.A
• Subjects: Access control; Classification techniques; Computer science; Computer security; Cybersecurity; Methods; Passwords; Pattern recognition; Statistical analysis; Studies; Classification techniques; Pattern recognition; Computer security; Passwords
• ISSN: 0167-4048; 1872-6208
• DOI: 10.1016/0167-4048(93)90083-H

A computer access verification methodology that uses pattern recognition techniques is presented in this paper. The input vectors were made up of the time intervals between successive keystrokes created by users while typing a known sequence of characters. Each input vector was classified into one of several classes, thereby identifying the user. Five pattern recognition techniques were used in this study. A 100% classification accuracy was achieved using the potential function algorithm, but this required the longest computing time. The least successful algorithm was the cosine measure, with an accuracy of 92.92% The application of these algorithms in identifying computer users could lead to more secure computer systems. This method is simple and accurate, with cost-effective characteristics.