PENERAPAN METODE EXTREME GRADIENT BOOSTING UNTUK DETEKSI MULTI-CLASSIFICATION SERANGAN SIBER

SANGSOKO, EDWAR AZY and Heryanto, Ahmad (2025) PENERAPAN METODE EXTREME GRADIENT BOOSTING UNTUK DETEKSI MULTI-CLASSIFICATION SERANGAN SIBER. Undergraduate thesis, Sriwijaya University.

Preview	Image RAMA_56201_09011382126160_COVER.jpg - Cover Image Available under License Creative Commons Public Domain Dedication. Download (5MB) | Preview
	Text RAMA_56201_09011382126160.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011382126160_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_56201_09011382126160_0022018703_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (718kB)
	Text RAMA_56201_09011382126160_0022018703_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (599kB) | Request a copy
	Text RAMA_56201_09011382126160_0022018703_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (488kB) | Request a copy
	Text RAMA_56201_09011382126160_0022018703_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011382126160_0022018703_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (147kB) | Request a copy
	Text RAMA_56201_09011382126160_0022018703_06_ref.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (212kB) | Request a copy
	Text RAMA_56201_09011382126160_0022018703_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (637kB) | Request a copy

Abstract

In the developing digital era, cybersecurity threats are increasing. One of the solutions commonly used in securing networks is the Network Intrusion Detection System (NIDS). To improve the performance of NIDS, this study applies the Machine Learning (ML) method, namely the Extreme Gradient Boosting (XGBoost) method, because it is considered to have high performance and its ability to handle complex and imbalanced data. Therefore, this study aims to evaluate the performance of the XGBoost algorithm in detecting various types of cyber attacks using five benchmark datasets commonly used in intrusion detection systems, namely NSL-KDD, UNSW-NB15, CIC-IDS2017, CSE-CIC-IDS2018, and ToN-IoT. In this study, XGBoost is used as the main algorithm to detect and classify various types of cyber attacks in the form of multi-class classification. Therefore, in this study has stages of pre-processing, feature selection, and hyperparameter tuning optimization. Also, several main evaluation metrics are used such as accuracy, precision, recall, F1-score, confusion matrix, and ROC-AUC.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Network Intrusion Detection System (NIDS), Machine Learning (ML), Extreme Gradient Boosting (XGBoost), multi-class classification, Hyperparameter Tuning.
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) > TA1-2040 Engineering (General). Civil engineering (General) > TA158.7 Computer network resources Including the Internet Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4150-4380 Computer network resources
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Edwar Azy Sangsoko
Date Deposited:	18 Sep 2025 05:04
Last Modified:	18 Sep 2025 05:04
URI:	http://repository.unsri.ac.id/id/eprint/184202

Actions (login required)

View Item