Skripsi

DETEKSI MALWARE TROJAN PADA LALU LINTAS JARINGAN REVERSE TCP DENGAN ALGORITMA DECISION TREE

---

Penilaian

---

Malware, short for malicious software, is a type of harmful software designed to damage, steal data from, or disrupt computer systems and networks. One of the most common types of malware is the Trojan, which typically disguises itself as a legitimate program but actually has malicious intent. To address this threat, a system is needed that can detect suspicious patterns in network traffic. This study aims to answer three main questions: how data is extracted from PCAP files, how effective the Decision Tree method is in detecting Trojan malware, and how to improve the performance of the detection model. The data extraction process was carried out using CICFlowMeter, which converts PCAP files into CSV format containing flow-based features of network traffic. The resulting data was then analyzed using Machine Learning methods, specifically the Decision Tree algorithm, to classify traffic as either normal or malicious. The results show that the Decision Tree method is effective in identifying malware activity on mobile network devices. The best performance before feature selection was achieved with a 25:25:50 training+validation-to-testing ratio, reaching an accuracy 93,15% and F1-score of 92.89%. After feature selection, the highest performance was obtained with a 40:40:20 ratio, achieving an accuracy 97,89% and F1-score of 97.89%. In addition, the implementation of the Snort intrusion detection system enhanced the detection process by recognizing attack patterns in the network traffic based on predefined rules. Feature selection played a crucial role in improving model performance by reducing overfitting and ensuring better generalization. Furthermore, optimizing the depth of the decision tree helped maintain a balance between bias and variance in the model. Keywords: Malware, Trojan, PCAP, Decision Tree, CICFlowMeter, Snort, Intrusion Detection, Feature Selection, Accuracy, F1-Score

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507003606	T176403	T1764032025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1764032025

Publisher

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

Collation

ix, 114 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