ENHANCED STACKED PADA LONG SHORT TERM MEMORY UNTUK MENINGKATKAN KEMAMPUAN KLASIFIKASI SERANGAN DDOS PADA DATASET CICDDOS 2019

ANJARWATI, CATURNING and Heryanto, Ahmad (2022) ENHANCED STACKED PADA LONG SHORT TERM MEMORY UNTUK MENINGKATKAN KEMAMPUAN KLASIFIKASI SERANGAN DDOS PADA DATASET CICDDOS 2019. Undergraduate thesis, Sriwijaya Univercity.

	Text RAMA_56201_09011281823056.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_56201_09011281823056_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (16kB) | Request a copy
Preview	Text RAMA_56201_09011281823056_0022018703_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_56201_09011281823056_0022018703_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011281823056_0022018703_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (280kB) | Request a copy
	Text RAMA_56201_09011281823056_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_09011281823056_0022018703_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7kB) | Request a copy
	Text RAMA_56201_09011281823056_0022018703_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (386kB) | Request a copy
	Text RAMA_56201_09011281823056_0022018703_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (748kB) | Request a copy

Abstract

Distributed Denial Of Service (DDoS) attacks are a type of cyber attack against websites. DDoS is marked by the amount of fake traffic that floods the server, system or internet network. As a result, the target website cannot be accessed because it is unable to manage too much traffic entering the server. There are three objectives in this research, including building a Long Shoer Term Memory Stacked model to classify DDoS attacks on network traffic records with the CICDDoS 2019 dataset. The second is to test the model in terms of time and resources needed when compared to existing models. The three produce the model with the best performance in the best performance in the classification of DDoS attacks. The Deep Learning method used is the BI-Directional LSTM method which is a branch of LSTM which has the advantage of having 2 layers, namely the forward layer and the backward layer so that it allows additional information enhancement and improves memory capabilities. This research was conducted by training the CIC-DDoS 2019 dataset on machine learning with the provision of tuning hyperparameters and comparing results with different ratios of training data and test data so that the best evaluation results were obtained with an accuracy value of 98.16%, precision 96.93 %, recall 99.39%, specificity 96.99% and f1 score 98.14%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	DDoS, LSTM, CIC-DDoS-2010 Dataset
Subjects:	T Technology > TH Building construction T Technology > TH Building construction > TH7005-7699 Heating and ventilation. Air conditioning T Technology > TJ Mechanical engineering and machinery > TJ1-1570 Mechanical engineering and machinery
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Caturning Anjarwati
Date Deposited:	19 Jan 2023 08:55
Last Modified:	19 Jan 2023 08:55
URI:	http://repository.unsri.ac.id/id/eprint/86531

Actions (login required)

View Item