PENERAPAN INTRUSION DETECTION SYSTEM DENGAN MENGGUNAKAN GATED RECURRENT UNIT (GRU) DALAM MENDETEKSI SERANGAN DDOS

AGUSTIANSYAH, DAFFA TEDI and Heryanto, Ahmad (2023) PENERAPAN INTRUSION DETECTION SYSTEM DENGAN MENGGUNAKAN GATED RECURRENT UNIT (GRU) DALAM MENDETEKSI SERANGAN DDOS. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011181924005.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011181924005_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011181924005_0022018703_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (919kB)
	Text RAMA_56201_09011181924005_0022018703_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (652kB) | Request a copy
	Text RAMA_56201_09011181924005_0022018703_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (461kB) | Request a copy
	Text RAMA_56201_09011181924005_0022018703_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (738kB) | Request a copy
	Text RAMA_56201_09011181924005_0022018703_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (184kB) | Request a copy
	Text RAMA_56201_09011181924005_0022018703_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (315kB) | Request a copy
	Text RAMA_56201_09011181924005_0022018703_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (387kB) | Request a copy

Abstract

Distributed Denial of Service or commonly abbreviated as DDoS is an attack commonly used by hackers to stop legitimate users from accessing certain network services and continue to send traffic to the target system continuously. DDoS attacks are usually carried out in two phases, namely the intuition phase where the attacker makes arrangements to launch the attack by creating a botnet which is a network of infected or malicious devices and the second phase, the settings on the botnet will be triggered to attack the target network. The method used in this research is the Gated Recurrent Unit (GRU). The advantage of GRU is that the GRU model is another advanced type of RNN that requires less time to train due to the simplicity of its gate structure. The research was conducted by detecting 2 classes of attacks, namely DDoS attacks and Benign attacks with validation results ranging from 10% to 90% of training data, on the hyper parameter number of Layers and Nodes, tanh and softmax activation, learning rate, batch size, optimizer, and loss. Based on the tests that have been carried out, the best results are obtained on 70% training data and 30% training data with an accuracy rate of 99.9995%, 100% recall, 99.9990% sensitivity, 100% precision, F1-score 99.9994%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Intrusion Detection System, Distributed Denial of Service, Deep Learning, Gated Recurrent Unit, Correlation-based Feature Selection.
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics > Q325.5 Machine learning 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:	Daffa Tedi Agustiansyah
Date Deposited:	23 Aug 2023 03:41
Last Modified:	23 Aug 2023 03:42
URI:	http://repository.unsri.ac.id/id/eprint/127737

Actions (login required)

View Item