MULTI CLASSIFICATION PADA SISTEM PENDETEKSI SERANGAN SIBER MENGGUNAKAN LSTM VARIANT

MAHARANI, REVI APRILIA and Heryanto, Ahmad (2023) MULTI CLASSIFICATION PADA SISTEM PENDETEKSI SERANGAN SIBER MENGGUNAKAN LSTM VARIANT. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011282025032.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (25MB) | Request a copy
	Text RAMA_56201_09011282025032_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (10MB) | Request a copy
	Text RAMA_56201_09011282025032_0022018703_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_56201_09011282025032_0022018703_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (370kB) | Request a copy
	Text RAMA_56201_09011282025032_0022018703_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (948kB) | Request a copy
	Text RAMA_56201_09011282025032_0022018703_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (22MB) | Request a copy
	Text RAMA_56201_09011282025032_0022018703_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (17kB) | Request a copy
	Text RAMA_56201_09011282025032_0022018703_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (161kB) | Request a copy
	Text RAMA_56201_09011282025032_0022018703_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (346kB) | Request a copy

Abstract

Long Short Term Memory, metode pendeteksi serangan siber dengan kemampuan memproses urutan data dan mengingat informasi dalam rentang waktu panjang. Namun, LSTM tidak dapat secara efektif mengingat informasi apabila urutan data terlalu panjang atau informasi tersebar pada jarak yang jauh. Oleh karena itu, hadir metode Bidirectional LSTM dan Stacked LSTM. BiLSTM mampu memproses urutan data secara simultan ke depan dan ke belakang, sehingga mampu menangkap konteks global dari data dan dapat memproses urutan data yang kompleks. Stacked LSTM, terdiri dari beberapa lapisan LSTM yang ditumpuk secara berurutan, sehingga mampu mendeteksi serangan siber dengan urutan data yang sangat panjang dan bervariasi. Penelitian ini mengidentifikasi metode yang paling efektif dalam klasifikasi serangan siber pada dataset multiclass, dengan mempertimbangkan kompleksitas dan karakteristik dataset CIC-IDS-2018, ISCXIDS2012, KDD Cup 1999, dan NSL-KDD. Validasi terbaik pada CIC-IDS-2018, Stacked LSTM dengan akurasi sebesar 86.99%. Pada ICXIDS2012, metode Stacked LSTM dengan akurasi 99.38%. Dataset KDD Cup 1999, Bidirectional LSTM dengan akurasi 99.08%. Pada dataset NSL-KDD, Bidirectional LSTM dengan akurasi 95.14%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	LSTM, Stacked LSTM, Bidirectional LSTM
Subjects:	Q Science > QA Mathematics > QA75-76.95 Calculating machines > QA75 Electronic computers. Computer science T Technology > TA Engineering (General). Civil engineering (General) > TA1-2040 Engineering (General). Civil engineering (General) > TA158.7 Computer network resources Including the Internet Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4150-4380 Computer network resources
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Revi Aprilia Maharani
Date Deposited:	17 Jan 2024 08:13
Last Modified:	17 Jan 2024 08:13
URI:	http://repository.unsri.ac.id/id/eprint/138196

Actions (login required)

View Item