EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Peningkatan Akurasi Deteksi Serangan Log Web Application Firewall Menggunakan Machine Learning

Mat Priyadi, Aini Suri Talita

Jurnal Informatika: Jurnal Pengembangan IT · 22.10.2026 · 11 (3) · 893-903

DOI: 10.30591/jpit.v11i3.29 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Jurnal Informatika: Jurnal Pengembangan IT, online erschienen am 22.10.2026. Verfasst von Mat Priyadi und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study aims to improve attack detection accuracy in Web Application Firewall (WAF) systems by applying a machine learning approach to log data. Conventional rule-based WAFs frequently suffer from high false-positive rates, which severely diminish security monitoring efficiency. This research utilizes a secondary dataset comprising 51,681 operational WAF log entries from the financial sector, covering SQL Injection, Cross-Site Scripting, and Command Injection. Preprocessing includes data cleaning, character-level n-gram TF-IDF feature extraction on URLs, and expert label relabeling to establish ground truth. Label verification reveals that 42.4% of initial WAF alerts are false positives (normal traffic). Two classification algorithms, Support Vector Machine (SVM) and K-Nearest Neighbors (KNN), are optimized across 71 hyperparameter tuning combinations and evaluated using Stratified 5-Fold Cross-Validation. Best model selection is conducted via the Simple Additive Weighting (SAW) method. Final test-set evaluation demonstrates that the polynomial-kernel SVM (C=10, gamma=scale, degree=3) achieves the highest performance with an accuracy of 0.9895, precision of 0.9859, recall of 0.9881, F1-score of 0.9870, and AUC of 0.9981. This approach effectively reduces false positives and provides reliable alert validation for real-world web environments

Zitieren

APA

Priyadi, M., & Talita, A. S. (2026). Peningkatan Akurasi Deteksi Serangan Log Web Application Firewall Menggunakan Machine Learning. Jurnal Informatika: Jurnal Pengembangan IT, 11(3), 893-903. https://doi.org/10.30591/jpit.v11i3.29

Vancouver

Priyadi M, Talita AS. Peningkatan Akurasi Deteksi Serangan Log Web Application Firewall Menggunakan Machine Learning. Jurnal Informatika: Jurnal Pengembangan IT. 2026;11(3):893-903. doi:10.30591/jpit.v11i3.29

BibTeX
@article{Priyadi2026,
  author = {Priyadi, Mat and Talita, Aini Suri},
  title = {Peningkatan Akurasi Deteksi Serangan Log Web Application Firewall Menggunakan Machine Learning},
  journal = {Jurnal Informatika: Jurnal Pengembangan IT},
  year = {2026},
  volume = {11},
  number = {3},
  pages = {893--903},
  doi = {10.30591/jpit.v11i3.29}
}
Kostenlos starten →