Culminating Project Title
Date of Award
Culminating Project Type
Information Assurance: M.S.
Information Assurance and Information Systems
Herberger School of Business
Dr. Akalanka Mailewa Dissanayaka
Dr. Mark Schmidt
Dr. Erich Rice
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Keywords and Subject Headings
Anomaly, Intrusion Detection, IDS, Dataset, Algorithm, Machine Learning
In today’s world, businesses and services are shifted to a digital transformation. As a result, network traffic has tremendously increased over the years. With that, network threats and attacks are growing and therefore, the importance of the Network Intrusion Detection System(NIDS) has increased. The traditional signature-based approach to intrusion detection is not sufficient to detect intrusions, so anomaly-based intrusion detection came into play. There are many methods to anomaly-based intrusion detection that can classify unknown network attacks. To detect network anomalies, Machine Learning and Deep Learning techniques are applied, and a considerable number of studies are done in this field. This paper presents classification models built using supervised Machine Learning algorithms. This study was conducted using algorithms like: Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Naïve Bayes, Decision Tree and Random Forest on multiple subsets of a realistic evaluation dataset i.e. CICIDS-2017. The result from this study shows that Random Forest outperforms other supervised Machine Learning algorithms with accuracy rate as high as 99.93% with 14 features selected using Pearson’s correlation coefficient method.
Jairu, Pankaj, "A Supervised Machine Learning Approach to Network Intrusion Detection on CICIDS-2017 Dataset" (2021). Culminating Projects in Information Assurance. 117.
Available for download on Saturday, December 17, 2022