Skripsi

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

---

Penilaian

---

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%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507003474	T175911	T1759112025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1759112025

Publisher

Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xiv, 128 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

004.07

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Sistem komputer

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment