WSEAS Transactions on Information Science and Applications
Print ISSN: 1790-0832, E-ISSN: 2224-3402
Volume 13, 2016
PaSSIL: A New Keystroke Dynamics System for Password Strengthening Based on Inductive Learning
Author:
Abstract: In this paper, anew inductive learning system, called PaSSIL, has been developed aims at strengthening the security of systems through keystroke dynamics against both online and offline attackers. The proposed system involves collecting data that represents the biometric patterns of users and converting this biometric data into features that can be manipulated by our inductive learning algorithm called ILA that produces inductive rules that are, in turn, used to classify the legitimate user (called the owner) from adversaries. This system is non-static and since features are a function of the user and the environment, it takes into consideration the gradual changes that happen in the way a user enters his password. Experiments have been conducted on data collected from hundreds of users and compared with our previous work and with some well-known systems. The results obtained are comparable with other systems if not better.
Search Articles
Pages: 80-92
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 13, 2016, Art. #9