OPTIMALISASI ALGORITMA LSTM PADA SISTEM PENDETEKSI SERANGAN BRUTEFORCE MENGGUNAKAN METODE BIDIRECTIONAL LSTM (BI-LSTM)

AGUSTINA, RIANTI and Heryanto, Ahmad (2023) OPTIMALISASI ALGORITMA LSTM PADA SISTEM PENDETEKSI SERANGAN BRUTEFORCE MENGGUNAKAN METODE BIDIRECTIONAL LSTM (BI-LSTM). Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011181924150.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9MB) | Request a copy
	Text RAMA_56201_09011181924150_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy
	Text RAMA_56201_09011181924150_0022018703_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (2MB)
	Text RAMA_56201_09011181924150_0022018703_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (894kB) | Request a copy
	Text RAMA_56201_09011181924150_0022018703_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011181924150_0022018703_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy
	Text RAMA_56201_09011181924150_0022018703_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (223kB) | Request a copy
	Text RAMA_56201_09011181924150_0022018703_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (367kB) | Request a copy
	Text RAMA_56201_09011181924150_0022018703_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (679kB) | Request a copy

Abstract

Bruteforce attack is a form of attack to be able to enter network services by making various pairs of usernames and passwords illegally. To avoid this attack you can use different character combinations such as alphabetic, alphanumeric, and alphanumeric with symbols. In an effort to protect network security systems against Bruteforce attacks, an attack detection system such as an Intrusion Detection System is needed. IDS is one of the detectors that can investigate activities that occur on internet systems and networks. The method used in this research is Bidirectional Long Short Term Memory (Bi-LSTM). In the Bi-LSTM method there is a structure that is different from a single LSTM, where Bi-LSTM can calculate input data sequentially and also in reverse order with the aim of obtaining two different external states (two directions). Besides that, the Bi-LSTM method also has a function to find out remote contextual dependencies. This study uses two types of attacks, namely FTP and SSH Bruteforce attacks taken from the CIC-IDS 2018 dataset. By validating training and testing data from 20% to 80%. As the output of this study, the best performance scores were Accuracy of 99.9923%, Recall of 99.9997%, Specificity of 99.9815%, Precision of 99.9900%, F1-Score of 99.9849%, and performance values of BACC of 99.9906% and MCC of 99.9848%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Bruteforce Attack, Intrusion Detection System, CIC-IDS 2018 Dataset, Bidirectional Long Short Term Memory.
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Rianti Agustina
Date Deposited:	04 Jul 2023 08:05
Last Modified:	04 Jul 2023 08:05
URI:	http://repository.unsri.ac.id/id/eprint/114178

Actions (login required)

View Item