Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : CommIT (Communication

Hybrid Stacking Model for Web Attack Classification Using LightGBM, Random Forest, and MLP Fadli Dony Pradana; Farikhin; Budi Warsito
CommIT (Communication and Information Technology) Journal Vol. 20 No. 1 (2026): CommIT Journal (in press)
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The research presents a stacking-based hybrid intrusion detection framework for web application attacks, addressing the persistent limitation that minority classes, including Brute Force, Cross-Site Scripting (XSS), and Structured Query Language (SQL) Injection, are frequently underdetected in conventional Intrusion Detection Systems (IDS) due to severe class imbalance. The proposed architecture combines LightGBM and Random Forest as base learners, while a Multi-Layer Perceptron (MLP) functions as the meta-learner. The framework is supported by rigorous preprocessing, ANOVA F-testbased feature selection, and domain-informed augmentation of critical traffic features, such as Flow Inter-Arrival Time (IAT) Min, Init Win bytes forward, and Backward (Bwd) Packets/s, through optimized weighting strategies. Evaluation on the CICIDS-2017 web attack subset using 10-fold stratified cross-validation shows that the proposed model improves the macro F1-Score from 0.62 ± 0.004 to 0.76 ± 0.003 and achieves a binary accuracy of 99.67% with a macro F1 of 0.94. The observed performance gains are statistically significant (p < 0.001), confirming the robustness of the framework. These findings indicate that targeted feature engineering and heterogeneous stacking substantially improve minority-attack detection while preserving majority-class performance. In addition, the framework demonstrates sub-millisecond inference time, highlighting its practical suitability for real-time IDS deployment in resource-constrained and high-throughput operational cybersecurity environments. The proposed design also offers methodological generalizability for broader anomaly detection tasks in dynamic network environments, where reliable recognition of low-frequency but high-impact attack patterns remains increasingly critically important.
Co-Authors A. Haris A. Rusgiyono Acep Irham Gufroni Adi Ariyo Munandar Adi Suliantoro Ahmad Abdul Chamid Ahmad Lubis Ghozali Aprilia, Maita Aris Sugiharto Arnelli Arnelli B. Raharjo Bambang Irawanto Bambang Irawanto Bambang Subeno Bayu Surarso Bayu Surarso Beta Noranita Bibit Waluyo Aji Budi Warsito Budi Warsito Carolin Carolin Catur Edi Widodo D. Ispriyanti Didik Setiyo Widodo Dinar Mutiara Kusumo Nugraheni Djuwandi Djuwandi DONNY IRAWAN MUSTABA Dwinta Rahmallah Pulukadang, Dwinta Rahmallah E. Setiawati Erikha Feriyanto Erlin Dwi Endarwati, Erlin Dwi Esti Wijayanti, Esti F. Ariyanto Fadli Dony Pradana Faozi, Safik Faudin, Arif Nur Fauzi, Irza Nur Feriyanto, Erikha Ferry Jie, Ferry Fitika Andraini H. Sutanto Heny Maslahah, Heny I. Marhaendrajaya Iswahyudi Joko Suprayitno J. E. Suseno Kartono . Keszya Wabang Kusworo Kusworo Laily Rahmania, Laily LM Fajar Israwan, LM Fajar M. Izzati M. Nur Madani, Faiq Mansur Mansur Meryta Febrilian Fatimah, Meryta Febrilian Mustafid Mustafid Neza Zhevira Septiani Nikken Prima Puspita Nikken Prima Puspita Nur Khasanah Oky Dwi Nurhayati Pangestika, Vidya Dwi Pradana, Fadli Dony Prantiastio Prastio, Wahyu Tedi Priyono Priyono Purwanto Purwanto R. Hariyati R. Hastuti Rachmat Gernowo Ratri Wulandari Retno Kusumaningrum Rezki Kurniati, Rezki Rineka Brylian Akbar Satriani Rinta Kridalukmana Robertus Heri Sulistyo Utomo S. Tana Safik Faozi, Safik Satriani, Rineka Brylian Akbar Siti Khabibah Siti Khabibah Sri Wahyuni Sugito Sugito Suhartono Suhartono Sunarsih . Suparti Suparti T. Windarti Titi Udjiani SRRM Toni Prahasto Udjiani , Titi Udjiani S.R.R.M, Titi Usman, Carissa Devina Uswatun Khasanah W. H. Rahmanto Wahyul Amien Syafei Wardani, Novita Koes Wardianto, Wardianto Warsito , Budi Wicaksono, Mahad Wyne Mumtaazah Putri Yosza Dasril Yully Estiningsih Z. Muhlisin