Citation

Quan, Ngee Wee and Goh, Hui Ngo and Lim, Amy Hui Lan (2025) Artificial intelligence-based intrusion detection system through ensemble approaches. In: 4th International Conference on Computer, Information Technology and Intelligent Computing, CITIC 2024, 23 July 2024 - 25 July 2024, Virtual, Online.

Text c-2.pdf - Published Version Restricted to Repository staff only Download (201kB)

Abstract

This paper explores the use of Artificial Intelligence (AI) to detect network intrusion on UNSW-NB15 dataset that is widely used due to its realism and completeness. The study focuses on exploratory data analysis and development of effective AI-based Intrusion Detection System (IDS). In exploratory data analysis, Pearson and Spearman coefficients are applied to understand the relationships between features in the UNSW-NB15 dataset. To prepare the UNSW-NB15 dataset as input to the AI-based IDS models, it will be pre-processed, followed by using the SelectKBest method with the Chi-squared statistic to identify relevant features. The detailed comparisons of various AI techniques and algorithms with emphasis on ensemble models using majority voting, stacking, bagging and boosting based on Decision Tree, Random Forest and Extra Trees are conducted for conceptualizing and developing effective AI-based IDS models. To ensure robustness of AI-based IDS models, both binary classification and multiclass classification are carried out to differentiate non-anomaly from other types of attack traffic records. The AI-based IDS models are measured using accuracy, precision, recall, and F1-score which give a detailed insight into performance of each model. It is observable that Random Forest seems to be consistently outperformed either as a single classifier or ensemble-based models.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Classification, ensemble model, imbalanced dataset, machine learning
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Nor Afiqah Mohd Adnan
Date Deposited:	09 Dec 2025 03:51
Last Modified:	13 Dec 2025 00:43
URII:	http://shdl.mmu.edu.my/id/eprint/14980

Downloads

Edit (login required)