REDUKSI DIMENSI FITUR SERANGAN BRUTEFORCE MENGGUNAKAN METODE AUTOENCODER LSTM (AE-LSTM) PADA SISTEM PENDETEKSI SERANGAN SIBER

UTAMI, RISTI AULIAH and Heryanto, Ahmad (2023) REDUKSI DIMENSI FITUR SERANGAN BRUTEFORCE MENGGUNAKAN METODE AUTOENCODER LSTM (AE-LSTM) PADA SISTEM PENDETEKSI SERANGAN SIBER. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011381924099.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy
	Text RAMA_56201_09011381924099_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (10MB) | Request a copy
	Text RAMA_56201_09011381924099_0022018703_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_56201_09011381924099_0022018703_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (715kB) | Request a copy
	Text RAMA_56201_09011381924099_0022018703_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (597kB) | Request a copy
	Text RAMA_56201_09011381924099_0022018703_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011381924099_0022018703_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (67kB) | Request a copy
	Text RAMA_56201_09011381924099_0022018703_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (168kB) | Request a copy
	Text RAMA_56201_09011381924099_0022018703_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (505kB) | Request a copy

Abstract

Bruteforce attack is an attack that uses the trial-error method to obtain user information, especially passwords. To overcome these problems, previous research has applied learning algorithms to cyber attack detection systems and obtained satisfactory results. In the cyber attack approach, there is a misdiagnosis that can arise due to high dimensional data. This study aims to apply the autoencoder algorithm as an attack feature dimension reduction method and the Long Short-Term Memory (LSTM) algorithm as a bruteforce attack classification method. The dataset used in this study is the CICIDS2018 dataset which contains Attack Data (FTP-Bruteforce and SSH-Bruteforce) and Normal Data (Benign). Data classification results obtained good accuracy of 99.9970%, with Recall of 99.9970%, Specificity of 99.9969%, Precision of 99.9969% and F1-Score of 99.9977%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Bruteforce, Cyber Attack, Intrusion Detection System (IDS), Autoencoder, LSTM, Dimensionality Reduction, Machine Learning.
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Risti Auliah Utami
Date Deposited:	04 Jul 2023 05:45
Last Modified:	04 Jul 2023 05:45
URI:	http://repository.unsri.ac.id/id/eprint/114151

Actions (login required)

View Item