Farhani Amanah, . (2026) SISTEM ANALISIS DAN KLASIFIKASI RISIKO MALICIOUS TRAFFIC PADA LOG HONEYPOT MENGGUNAKAN ALGORITMA RANDOM FOREST. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (170kB) |
|
Text
AWAL.pdf Download (612kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (281kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (626kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (640kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 5.pdf Download (242kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (243kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository staff only Download (88kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (28MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (555kB) |
Abstract
The increasing volume and sophistication of cyber threats have resulted in a growing amount of malicious traffic recorded by honeypots, creating the need for a mechanism capable of identifying attack risk levels in a measurable manner. This study aims to develop a risk analysis and classification system for malicious traffic based on honeypot logs using the Random Forest algorithm. The dataset was obtained from honeypot logs that record authentication activities and attacker interactions. The research process consisted of data preprocessing, feature engineering, risk label generation using pseudo labeling based on the MITRE ATT&CK framework and NIST SP 800-30, data balancing using the Synthetic Minority Oversampling Technique (SMOTE), and model evaluation through Stratified 5-Fold Cross Validation. The results show that the Random Forest model successfully classified malicious traffic into Low Risk and High Risk categories, achieving an accuracy of 99,40%, precision of 95,28%, recall of 99,02%, F1-score of 97,12%, and ROC-AUC of 99,95%. The model was subsequently implemented in a web-based dashboard to provide interactive analysis results, risk classification, attack indications, and security recommendations. These findings demonstrate that the combination of honeypot logs and Random Forest is effective in supporting cyber threat risk analysis based on attack behavior characteristics.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2210511021] [Pembimbing 1: Supriyanto] [Pembimbing 2: Kharisma Wiati Gusti] [Penguji 1: Widya Cholil] [Penguji 2: Anis Fitri Nur Masruriyah] |
| Uncontrolled Keywords: | malicious traffic, honeypot, Random Forest, risk classification, cybersecurity |
| Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | FARHANI AMANAH |
| Date Deposited: | 28 Jul 2026 07:30 |
| Last Modified: | 28 Aug 2026 06:22 |
| URI: | http://repository.upnvj.ac.id/id/eprint/51562 |
Actions (login required)
 |
View Item |