Skripsi

DETEKSI ADVANCED PERSISTENT THREAT (APT) PADA CYBER THREAT INTELLIGENCE (CTI) MENGGUNAKAN DECISION TREE DAN RANDOM FOREST

---

The development of information technology has increased cyber attack threats, especially Advanced Persistent Threat (APT), so appropriate methods are needed to detect attacks based on Cyber Threat Intelligence (CTI) data. The main problems in this study are data imbalance and the difficulty in determining the most important features to improve detection results. To address these problems, this study uses a machine learning pipeline that combines Decision Tree for important feature selection, followed by Random Forest as the classification model, with the application of SMOTE and random undersampling to handle data imbalance, as well as evaluation using a confusion matrix and derived metrics such as TPR, FPR, TNR, FNR, and accuracy. The results show that after handling data imbalance, the model maintains very high performance across all attack classes, with accuracy values close to 1.0 for all classes. These results indicate that the Decision Tree Random Forest pipeline is effective and reliable for detecting APT attacks on the CTI dataset. Keywords: Cyber Attack Detection, Advanced Persistent Threat, Cyber Threat Intelligence, Decision Tree, Random Forest

---

Availability

Detail Information

Series Title

-

Call Number

T1932792026

Publisher

Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026

Collation

xiv, 48 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

005.807

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Sistem Komputer
Advanced Persistent Threat

Specific Detail Info

-

Statement of Responsibility

KA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment