OPTIMALISASI MULTI-CLASSIFICATION SERANGAN CYBER MENGGUNAKAN METODE K-NEAREST NEIGHBOR

YANTI, ZULI and Heryanto, Ahmad (2024) OPTIMALISASI MULTI-CLASSIFICATION SERANGAN CYBER MENGGUNAKAN METODE K-NEAREST NEIGHBOR. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011182025014.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (23MB) | Request a copy
	Text RAMA_56201_09011182025014_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (17MB) | Request a copy
	Text RAMA_56201_09011182025014_0022018703_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (2MB)
	Text RAMA_56201_09011182025014_0022018703_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (608kB) | Request a copy
	Text RAMA_56201_09011182025014_0022018703_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (819kB) | Request a copy
	Text RAMA_56201_09011182025014_0022018703_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (19MB) | Request a copy
	Text RAMA_56201_09011182025014_0022018703_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (10kB) | Request a copy
	Text RAMA_56201_09011182025014_0022018703_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (140kB) | Request a copy
	Text RAMA_56201_09011182025014_0022018703_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (322kB) | Request a copy

Abstract

Cyber attacks are a form of threat aimed at stealing, damaging, or altering important data within computer systems or networks. These attacks include hacking, phishing, and malware. Detecting cyber attacks is crucial to maintaining the security of information systems from increasing threats. One tool used for threat detection is Intrusion Detection Systems (IDS), which monitor system events and take action if there are suspicious activities or attacks. In efforts to enhance IDS performance, research has explored the use of Artificial Intelligence (AI), particularly Machine Learning (ML) techniques. This study focuses on implementing the K-Nearest Neighbors (K-NN) method, a non-parametric technique for measuring the distance between new and previously classified data using Euclidean distance. To test the effectiveness of the K-NN method, various datasets are utilized, including UNSW-NB15, NSL-KDD, ISCX2012, and CIC-IDS-2018. The research findings indicate that the model achieves high accuracy rates on each dataset during the training process, namely 88.00% on the UNSW-NB15 dataset, 99.99% on the NSL-KDD dataset, 99.96% on the ISCX2012 dataset, and 92.00% on the CIC-IDS-2018 dataset.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	KNN, Serangan Siber, UNSW-NB15, NSL-KDD, ISCX2012, CIC-IDS-2018
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Zuli Yanti
Date Deposited:	05 Apr 2024 02:38
Last Modified:	05 Apr 2024 02:38
URI:	http://repository.unsri.ac.id/id/eprint/143138

Actions (login required)

View Item