KLASIFIKASI MALICIOUS URL PADA FILE BERBASIS HOST-BASED FEATURE EXTRACTION MENGGUNAKAN METODE BI-DIRECTIONAL LSTM

PUTRA, MUHAMMAD ANDIKO and Heryanto, Ahmad (2025) KLASIFIKASI MALICIOUS URL PADA FILE BERBASIS HOST-BASED FEATURE EXTRACTION MENGGUNAKAN METODE BI-DIRECTIONAL LSTM. Undergraduate thesis, Sriwijaya University.

	Image RAMA_56201_09011281823048_cover.jpg - Cover Image Available under License Creative Commons Public Domain Dedication. Download (172kB)
	Text RAMA_56201_09011281823048.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011281823048_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_09011281823048_0022018703_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (853kB)
	Text RAMA_56201_09011281823048_0022018703_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (604kB) | Request a copy
	Text RAMA_56201_09011281823048_0022018703_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (469kB) | Request a copy
	Text RAMA_56201_09011281823048_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_09011281823048_0022018703_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (77kB) | Request a copy
	Text RAMA_56201_09011281823048_0022018703_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (150kB) | Request a copy
	Text RAMA_56201_09011281823048_0022018703_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (343kB) | Request a copy

Abstract

The advancement of technology had led to an increasing variety of attacks or threats targeting internet users. Attacks such as phishing, malware, spyware, and ransomware were the common types that targeted internet users. One of the most effective attack methods at the time was through the use of URLs. A URL (Uniform Resource Locator) was an address used to locate a file on the Internet. This made URLs one of the methods used to carry out cyberattacks, known as Malicious URLs. Malicious URLs or harmful websites on the internet contained various types of content such as spam and phishing, which were used to initiate attacks. In this study, PDF files from Garba Rujukan Digital were used by extracting the URLs contained in each PDF file, which were then parsed to create a dataset consisting of benign and malicious data. The resulting dataset was classified using a Bi-Directional LSTM (Long Short Term Memory) with host-based feature extraction. The training data was divided using various ratios: 50:50, 40:60, 30:70, 20:80, and 10:90. Hyperparameter tuning was applied during the data training process, particularly with the 50:50 data ratio. The classification performance of the Malicious URL model proved to be effective, achieving an accuracy of 93.35%, a precision of 96.79%, a recall of 89.67%, and a specificity of 97.03%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Malicious URL, Bi-Directional LSTM
Subjects:	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:	Muhammad Andiko Putra
Date Deposited:	24 Jun 2025 06:41
Last Modified:	24 Jun 2025 06:41
URI:	http://repository.unsri.ac.id/id/eprint/175911

Actions (login required)

View Item