Salwa Nafisa, . (2026) IMPLEMENTASI SISTEM KLASIFIKASI SERANGAN DDOS BERBASIS WEBSITE DENGAN KOMPARASI MODEL MACHINE LEARNING. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (529kB) |
|
Text
AWAL.pdf Download (2MB) |
|
Text
BAB I.pdf Restricted to Repository UPNVJ Only Download (2MB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (12MB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (11MB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (24MB) |
|
Text
BAB V.pdf Download (742kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (1MB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (95kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (2MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (23MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (431kB) |
Abstract
Distributed Denial of Service (DDoS) attacks can disrupt service availability by overwhelming networks or servers with traffic from multiple sources. This study aims to develop a web-based DDoS classification system and compare the performance of Logistic Regression, Decision Tree, Random Forest, and XGBoost. The SNT dataset contains 1,034,668 flow-based traffic records. Four identity-related attributes were excluded, leaving 17 input features. Identical feature patterns were grouped, and the data were split using StratifiedGroupKFold to reduce the risk of pattern leakage. The models were evaluated using accuracy, precision, recall, F1-score, confusion matrix, ROC-AUC, and group-based cross-validation, then selected using the Weighted Sum Method. In the initial comparison using 17 features, XGBoost achieved 99.9104% accuracy, 99.8187% precision, 99.9980% recall, a 99.9083% F1-score, an AUC of 0.9999, and a WSM score of 0.9547. After the feature-reduction experiment, a six-feature XGBoost model was selected as the final model and integrated into a Flask application. Black-box testing by three testers across 21 scenarios achieved a 100% success rate. The system also processed 1,000,000 rows in an average total time of 3.3080 seconds.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2210511051] [Pembimbing 1: Supriyanto] [Pembimbing 2: Nur Hafifah Matondang] [Penguji 1: Widya Cholil] [Penguji 2: Hamonangan Kinantan Prabu] |
| Uncontrolled Keywords: | DDoS, XGBoost, Classification, StratifiedGroupKFold, Web Application |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | SALWA NAFISA |
| Date Deposited: | 29 Jul 2026 13:56 |
| Last Modified: | 29 Jul 2026 13:56 |
| URI: | http://repository.upnvj.ac.id/id/eprint/52127 |
Actions (login required)
 |
View Item |