Zainuddin, Muhammad (2026) Pengembangan Sistem Keamanan Aplikasi Website Menggunakan Web Application Firewall Dengan Pendekatan Machine Learning. Undergraduate thesis, Universitas Hayam Wuruk Perbanas.
![[img]](http://eprints.perbanas.ac.id/style/images/fileicons/text.png) |
Text
ARTIKEL ILMIAH.pdf Restricted to Registered users only Download (534kB) |
|
|
Text
COVER.pdf Restricted to Registered users only Download (565kB) |
|
|
Text
BAB I.pdf Download (259kB) | Preview |
|
|
Text
BAB II.pdf Restricted to Registered users only Download (768kB) |
|
|
Text
BAB III.pdf Restricted to Registered users only Download (680kB) |
|
|
Text
BAB IV.pdf Restricted to Registered users only Download (668kB) |
|
|
Text
BAB V.pdf Download (258kB) | Preview |
|
|
Text
LAMPIRAN.pdf Restricted to Registered users only Download (3MB) |
Abstract
The increasing use of web-based applications in higher education environments, including electronic voting (e-vote) systems for selecting student organization leaders, requires reliable security mechanisms to protect systems from cyberattacks such as SQL Injection and Cross-Site Scripting (XSS). This study aims to develop and implement a Machine Learning-based Web Application Firewall (WAF) that is adaptive and directly integrated into a web-based e-vote application. The main contribution of this research lies in the integration of a Machine Learning model into a WAF system that is evaluated not only theoretically but also functionally through end-to-end system testing. The core idea of this study is to utilize a supervised learning approach to classify HTTP traffic into benign and malicious requests, enabling automatic attack prevention. The research procedures include collecting attack payload datasets, text data preprocessing, training and evaluating Decision Tree and Random Forest models, and integrating the best-performing model into the WAF middleware. System testing is conducted using functional testing and black box testing approaches in a localhost environment with the assistance of Postman. The results indicate that for SQL Injection detection, the Decision Tree model achieves a high accuracy of approximately 99.25%, while the Random Forest model provides a higher accuracy of approximately 99.54%. For XSS detection, the Decision Tree model reaches a very high accuracy of approximately 99.94%, whereas the Random Forest model achieves perfect accuracy of 100%. The implications of this study demonstrate that a Machine Learning-based WAF, particularly using the Random Forest model, is effective as an additional security layer for protecting critical web applications in higher education environments.
| Item Type: | Thesis (Undergraduate) |
|---|---|
| Subjects: | 000 - COMPUTER SCIENCE, INFORMATION, GENERAL WORKS > 000 - 009 COMPUTER SCIENCE, INFORMATION, GENERAL WORKS > 000 - COMPUTER SCIENCE, INFORMATION, GENERAL WORKS 000 - COMPUTER SCIENCE, INFORMATION, GENERAL WORKS > 000 - 009 COMPUTER SCIENCE, INFORMATION, GENERAL WORKS > 005 - COMPUTER PROGRAMMING, PROGRAMS & DATA |
| Divisions: | Bachelor of Informatics |
| Depositing User: | MUHAMMAD ZAINUDDIN |
| Date Deposited: | 04 May 2026 01:54 |
| Last Modified: | 04 May 2026 01:54 |
| URI: | http://eprints.perbanas.ac.id/id/eprint/14100 |
Actions (login required)
 |
View Item |