Abstract—The purpose of this research was to study the
concept and architectural design for Risk Assessment (RA) for
information system with the Canadian Institute for
Cybersecurity Intrusion Detection Systems 2017 dataset
(CICIDS2017 dataset) using Machine Learning (ML) to
establish a model. It evaluated the risk on detected network
data. The results indicated, the concept consisted of input such
as CICIDS2017 dataset, ML, network data and risk matrix.
Information system real time RA using CICIDS2017 dataset
and ML were processes and the RA on the system were
outcomes. In addition, the concept components were improved
upon and comprised of four sections; 1) network data capture
for network data collection, 2) CICIDS2017 that was intrusion
dataset for establishment of a predictive model with ML
algorithm, 3) classification predictive model, forecasted on
intrusion from network data and 4) RA report, estimated risk
of information in risk matrix format. Finally, architectural
design, consists of three major parts which includes; network
data capture, risk predictive analysis and RA report.
Index Terms—Real time risk assessment, information
system, CICIDS2017 dataset, machine learning.
The authors are with the Division of Information and Communication
Technology for Education, Faculty of Technical Education, King Mongkut’s
University of Technology North Bangkok (KMUTNB), Bangkok, Thailand
(e-mail: preecha@yru.ac.th, prachyanun.n@fte.kmutnb.ac.th,
panita.w@fte.kmutnb.ac.th).
Cite: Preecha Pangsuban, Prachyanun Nilsook, and Panita Wannapiroon, "A Real-time Risk Assessment for Information System with CICIDS2017 Dataset Using Machine Learning," International Journal of Machine Learning and Computing vol. 10, no. 3, pp. 465-470, 2020.
Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).