Introducing a Machine Learning Password Metric Based on EFKM Clustering Algorithm

Omar Saad Almousa; Hazem Migdady

No Detail Found!

Introducing a Machine Learning Password Metric Based on EFKM Clustering Algorithm

Author(s)

Omar Saad Almousa Computer Science Department, Jordan University of Science and Technology,,Jordan

Hazem Migdady Computer Science and Management Information Systems Department, Oman College of Management and Technology,,Oman

Abstract

we introduce a password strength metric using the Enhanced Fuzzy K-Means clustering algorithm (EFKM henceforth). We train the EFKM on the OWASP list of 10002 weak passwords. After that, we maximize the optimized centroids to develop a password strength metric. We validate the resulting meter by contrasting with three entropy-based metrics using two datasets: the training dataset (OWASP) and a dataset we collected from the GitHub website that contains 5189451 leaked passwords. Our metric can recognize all the passwords from the OWASP as weak passwords only. Regarding the leaked passwords, the metric recognizes almost the entire set as weak passwords. We found that the results of the EFKM-based metric and the entropy-based meters are consistent. Hence the EFKM metric shows its validity as an efficient password strength checker.

Publication Details

Page(s) 394-400

DOI DOI not available

Published Journal: International Journal of Communication Networks and Information Security, Volume: 12, Issue: 3, Year: 2020

Request the full text from PASTIC

Keywords

entropy, Clustering, OWASP, Password Strength Metric, Leaked Passwords., EFKM, Weak Passwords

Citations

Downloads

Views