DETEKSI SERANGAN DDOS DENGAN INTRUSION DETECTION SYSTEM MENGGUNAKAN METODE BIDIRECTIONAL RNN

SUJANA, JEPI and Heryanto, Ahmad (2022) DETEKSI SERANGAN DDOS DENGAN INTRUSION DETECTION SYSTEM MENGGUNAKAN METODE BIDIRECTIONAL RNN. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011281823061.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_56201_09011281823061_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9MB) | Request a copy
Preview	Text RAMA_56201_09011281823061_0022018703_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_56201_09011281823061_0022018703_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (587kB) | Request a copy
	Text RAMA_56201_09011281823061_0022018703_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (690kB) | Request a copy
	Text RAMA_56201_09011281823061_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_09011281823061_0022018703_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (13kB) | Request a copy
	Text RAMA_56201_09011281823061_0022018703_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (98kB) | Request a copy
	Text RAMA_56201_09011281823061_0022018703_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (619kB) | Request a copy

Abstract

DDoS attacks can cause targeted servers to become slow and web server services unavailable, but DDoS attacks are difficult to detect in a network because their traffic patterns are similar to those of legitimate clients, because attackers emulate their attack traffic among legitimate traffic to hide their attacks. In this study, datasets originating from CSE-CIC-IDS 2018 were used. There are three objectives in this study. The first is the implementation of the Corelation-based Feature Selection (CFS) feature in order to obtain important features during the attack detection process. The second is the application of the Bidirectional RNN method to detect DDoS attacks. The third is knowing the results of DDoS attack detection performance seen from the results of the values for accuracy, precision, sensitivity, specificity, F1-Score, BAAC and MMC. The deep learning method used is Bidirectional RNN, which is a branch of RNN which can duplicate the RNN processing chain so that the input can be processed in the order of the backward layer and the forward layer so that it is possible to provide an increase in high accuracy results. This research has three benefits, the first is providing optimization in terms of computation time, the second is applying the Bidirectional RNN method to detect DDoS attacks, and the third is providing the best performance when the detection process is using the Bidirectional RNN method. This research was conducted by training the CSE-CIC-IDS 2018 dataset on machine learning by tuning hyper parameters and comparing the ratios of different training data and test data so as to produce the best evaluation value with an accuracy value of 99.9954%, 99.9905% recall, 100% specificity, 100% precision, F1-Score 99.9954%, and performance BACC 99.9954%, and MCC 99.9908%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	DDoS, RRN
Subjects:	T Technology > T Technology (General) > T58.5-58.64 Information technology > T58.6.E9 Management information systems -- Congresses.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Jepi Sujana
Date Deposited:	09 Jan 2023 08:36
Last Modified:	09 Jan 2023 08:36
URI:	http://repository.unsri.ac.id/id/eprint/85572

Actions (login required)

View Item