One of the most popular access-control mechanisms is Role-based access control (RBAC) because it is convenience for the management and various security policies. Clustering is an unsupervised machine learning process that creates clusters such that data points inside a cluster share similar characteristics patterns. However, clustering is still a challenging task since many cluster algorithms fail to do well in scaling with the size of the data set and the number of dimensions that describe the points. The main aim of this project to study how to use the machine learning technique for clustering RBAC data set and modified it.
CLUSTERING ROLE-BASED ACCESS CONTROL DATASET USING MODIFIED MACHINE LEARNING ALGORITHM
1. CLUSTERING ROLE-BASED
ACCESS CONTROL
DATASET USING
MODIFIED MACHINE
LEARNING ALGORITHM
One of the most popular access-control mechanisms is Role-based access control (RBAC)
because it is convenience for the management and various security policies. Clustering is an
unsupervised machine learning process that creates clusters such that data points inside a
cluster share similar characteristics patterns. However, clustering is still a challenging task
since many cluster algorithms fail to do well in scaling with the size of the data set and the
number of dimensions that describe the points. The main aim of this project to study how to
use the machine learning technique for clustering RBAC data set and modified it.
NURUL ANIS BINTI RASIDI
BTBL18049919
BACHELOR OF COMPUTER SCIENCE IN COMPUTER NETWORK SECURITY WITH HONOURS
UNIVERSITY OF SULTAN ZAINAL ABIDIN (UniSZA)
CIK NAZIRAH ABD HAMID
To study the use of the machine learning
technique for clustering RBAC data set.
To apply a modified machine learning
technique to cluster RBAC data set.
To test the efficiency of the modified
technique to cluster the RBAC data set.
OBJECTIVES FRAMEWORK
ABSTRACT
CONTRIBUTION
In this project, K-means algorithm has been
proven to be suitable for RBAC data set. K-
means algorithm uses Euclidean distance as
distance measure, so in this project, we
modified the K-means algorithm with other
distance measure. From the implementation
and testing, Chebyshev distance can perform
better that Euclidean distance in RBAC data
set.