Skripsi

DETEKSI AKSES JUDI ONLINE VIA TLS/SSL MENGGUNAKAN METODE RANDOM FOREST

---

Penilaian

---

This study aims to detect access to online gambling sites encrypted with TLS/SSL using machine learning-based network traffic fingerprint analysis, without accessing content to maintain privacy. The background focuses on the prevalence of illegal online gambling hidden behind encryption, which reduces the effectiveness of traditional methods such as DPI. The problem formulation includes the identification of encrypted traffic, significant statistical features (packet size, data volume, session duration, exchange frequency), and Random Forest evaluation. The methodology includes literature studies, expert consultations, COMNETS dataset collection (PCAP), feature extraction with Tshark, preprocessing (cleaning, encoding, splitting, normalization, balancing), and Random Forest training (with variations in the number of trees (64 and 256) and data ratio (80:20, 70:30, 40:60, 60:40). The results show the best performance in the 64 trees configuration with an 80:20 ratio, achieving an accuracy of 99.2%, precision of 99.5%, recall of 93.9%, and an F1-score of 96.6%. Key features such as tls.handshake.extensions_server_name and total_tcp_len_dst proved to be significant in distinguishing online gambling traffic from normal traffic. Thus, the Random Forest model proved to be effective for detecting encrypted online gambling site access.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507006190	T185460	T1854602025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1854602025

Publisher

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

Collation

xiv, 103 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

519.207

Content Type

Text

Media Type

unmediated

Carrier Type

other (computer)

Edition

-

Subject(s)

Prodi Sistem Komputer
Teori Deteksi

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment