KLASIFIKASI SERANGAN BOTNET PADA INTRUSION DETECTION SYSTEM MENGGUNAKAN METODE LONG SHORT TERM MEMORY STACKED

PERTIWI, HANNA and Heryanto, Ahmad (2022) KLASIFIKASI SERANGAN BOTNET PADA INTRUSION DETECTION SYSTEM MENGGUNAKAN METODE LONG SHORT TERM MEMORY STACKED. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011281823037.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011281823037_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy
Preview	Text RAMA_56201_09011281823037_0022018703_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (3MB) | Preview
	Text RAMA_56201_09011281823037_0022018703_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011281823037_0022018703_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (926kB) | Request a copy
	Text RAMA_56201_09011281823037_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_09011281823037_0022018703_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (32kB) | Request a copy
	Text RAMA_56201_09011281823037_0022018703_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (890kB) | Request a copy
	Text RAMA_56201_09011281823037_0022018703_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (588kB) | Request a copy

Abstract

Botnets are one of the most serious threats to the internet because they are able to provide a platform that can be distributed to illegal activities such as various attacks on the internet. One of the capabilities of a botnet that differentiates it from other malware is that it can be controlled remotely by a bootmaster under a command and control channel (C&C) channel infrastructure. There are two objectives in this research, among others, to build a model for the Stacked LSTM method to classify Botnet attack forms on IDS traffic based on the 2018 CIC-IDS dataset. Second, produce the model with the best performance. Therefore, to overcome the previous problem, the deep learning method was used. The Deep Learning method used is the Stacked LSTM method which is a branch of LSTM. In this study, the Principal Component Analysis (PCA) technique was used to reduce dimensions and training time efficiency, the Synthetic Minority Over-Sampling Technique (SMOTE) technique was also applied to balance the dataset to be processed, then Hyperparameter Tuning was applied to see the best parameters to be applied. on research models. Research validation was carried out 5 times in the study. The best validation results from the overall results were at 90% training data and 10% testing data where in this study the results obtained were 99.46% accuracy points, 99.86% recall, 99.06% specificity, 99.07% precision, and F1 score 99.46%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Pengetahuan Guru, Pemodelan Matematika
Subjects:	Q Science > QA Mathematics > QA8.9-QA10.3 Computer science. Artificial intelligence. Computational complexity. Data structures (Computer scienc. Mathematical Logic and Formal Languages
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Hanna Pertiwi
Date Deposited:	06 Jan 2023 07:59
Last Modified:	06 Jan 2023 07:59
URI:	http://repository.unsri.ac.id/id/eprint/85440

Actions (login required)

View Item