Deteksi Intrusi Jaringan Berbasis Machine Learning Menggunakan Model Boosting dengan Session-Level Feature Representation
-
Mochamad Sanwasih
*
Politeknik Digital Boash Indonesia, Bogor,
Indonesia
- Fajar Septian Politeknik Negeri Jakarta, Depok, Indonesia
- Ristasari Dwi Septiana Institut Teknologi dan Bisnis Swadharma, Jakarta, Indonesia (*) Corresponding Author
Abstract
The increasing complexity of network security threats demands intrusion detection systems that are both contextual and adaptive. Conventional signature-based Intrusion Detection Systems (IDS) suffer from limitations in detecting emerging and previously unseen attack patterns, making machine learning–based approaches a more flexible alternative. However, fragmented packet-level feature representations still limit the ability of models to capture network behavior comprehensively. This study aims to evaluate the performance of boosting models, namely XGBoost and LightGBM, using the publicly available Cybersecurity Intrusion Detection Dataset from Kaggle, which represents network activity at the session level. The proposed approach develops a session-level feature representation based on aggregated and ratio-based features to capture network behavior characteristics more comprehensively. Experimental results demonstrate that the implementation of session-level feature representation yields consistent improvements across multiple evaluation metrics. Accuracy increased from 0.8779 to 0.8847, while the F1-score improved from 0.8452 to 0.8525 for XGBoost and from 0.8455 to 0.8523 for LightGBM. Furthermore, ROC-AUC increased from 0.8789 to 0.8844 for XGBoost and from 0.8793 to 0.8859 for LightGBM. Although the improvement in accuracy is relatively moderate, the gains in F1-score and ROC-AUC indicate enhanced discriminative capability and a better balance between precision and recall. The main contribution of this study lies in the integration of session-level feature engineering with boosting models within a systematic evaluation framework, emphasizing the critical role of behavioral feature representation in improving intrusion detection performance.
Downloads
References
P. A. Khairunnisa, N. Annisa, Y. Yukandri, and J. Parhusip, “Perancangan Sistem Keamanan Jaringan Berbasis Cybersecurity untuk Mitigasi Ancaman Siber pada Infrastruktur TI: Studi Kasus di Indonesia,” Tek. J. Ilmu Tek. dan Inform., vol. 4, no. 2, pp. 9–16, 2024, doi: https://doi.org/10.51903/teknik.v3i1.570.
T. Widodo and A. S. Aji, “Pemanfaatan Network Forensic Investigation Framework untuk Mengidentifikasi Serangan Jaringan Melalui Intrusion Detection System (IDS),” JISKA (Jurnal Inform. Sunan Kalijaga), vol. 7, no. 1, pp. 46–55, 2022, doi: https://doi.org/10.14421/jiska.2022.7.1.46-55.
D. Firdaus, F. Fahira, and R. Rianti, “Deteksi Anomali dan Serangan Low Rate Ddos Dalam Lalu Lintas Jaringan Menggunakan Naive Bayes,” NARATIF J. Ilm. Nas. Ris. Apl. dan Tek. Inform., vol. 05, no. 02, pp. 140–148, 2023, doi: https://doi.org/10.53580/naratif.v5i2.208.
C. Chandra, D. Prima, and F. Faradika, “Deteksi Serangan Siber Menggunakan Machine Learning: Studi Pada Sistem Informasi Akademik,” JISKA J. Sist. Inf. Dan Inform., vol. 3, no. 2, pp. 106–110, 2025, doi: https://doi.org/10.47233/jiska.v3i2.2139.
A. T. Zy, A. T. Sasongko, and A. Z. Kamalia, “Penerapan Naïve Bayes Classifier, Support Vector Machine, dan Decision Tree untuk Meningkatkan Deteksi Ancaman Keamanan Jaringan,” KLIK Kaji. Ilm. Inform. dan Komput., vol. 4, no. 1, pp. 610–617, 2023, doi: https://doi.org/10.30865/klik.v4i1.1134.
R. Rio and K. Handoko, “Analisis Perbandingan Kinerja Algoritma Machine Learning Berbasis Feature Selection Dalam Deteksi Serangan Botnet,” J. Comasie, vol. 12, no. 2, pp. 139–148, 2025, doi: https://doi.org/10.33884/comasiejournal.v12i2.9778.
D. P. Sari, Z. Halim, B. Waseso, and S. Saromah, “Implementasi Machine Learning untuk Deteksi Intrusi pada Jaringan Komputer,” J. Minfo Polgan, vol. 13, no. 2, pp. 1389–1394, 2024, doi: https://doi.org/10.33395/jmp.v13i2.14074.
W. Alexander and D. Jollyta, “Sistem Deteksi Intrusi Pada Jaringan Komputer Menggunakan Algoritma XGBoost,” J. Mhs. Apl. Teknol. Komput. dan Inf., vol. 7, no. 2, pp. 128–134, 2025, doi: https://doi.org/10.35145/jmapteksi.v7i2.4969.
F. Pratama, E. Ali, R. Rahmaddeni, and W. Agustin, “Perbandingan Kinerja XGBoost dan LightGBM Dalam Klasifikasi Depresi Pada Mahasiswa Berdasarkan Faktor Demografi dan Akademik,” J. Algoritm., vol. 22, no. 2, pp. 53–64, 2025, doi: https://doi.org/10.33364/algoritma/v.22-2.2439.
R. Gunawan, E. S. Handika, and E. Ismanto, “Pendekatan Machine Learning Dengan Menggunakan Algoritma XGBoost (Extreme Gradient Boosting) Untuk Peningkatan Kinerja Klasifikasi Serangan Syn,” J. Comput. Sci. Inf. Technol., vol. 3, no. 3, pp. 453–463, 2022, doi: https://doi.org/10.37859/coscitech.v3i3.4356.
T. Wulandari, Y. F. Yudisthira, K. Chika, M. A. Wibowo, and C. Andrew, “Algoritma LightGBM untuk Deteksi Aktivitas Cyber Espionage Melalui Dataset Serangan Siber,” JUSIFOR J. Sist. Inf. dan Inform., vol. 4, no. 1, pp. 213–219, 2025, doi: https://doi.org/10.70609/jusifor.v4i2.8489.
A. R. Kamila, F. Adikara, S. Sutrisno, and C. Herdian, “Analisa Pengaruh Penambahan Fitur dengan Perbandingan Algoritma berbasis Bagging dan Boosting pada Deteksi Phishing Link,” JEPIN (Jurnal Edukasi dan Penelit. Inform., vol. 10, no. 3, pp. 460–467, 2024, doi: https://doi.org/10.26418/jp.v10i3.83366.
I. Ahmad, Y. Rahmanto, R. I. Borman, F. Rossi, Y. Jusman, and A. D. Alexander, “Identification of Pineapple Disease Based on Image Using Neural Network Self-Organizing Map (SOM) Model,” in International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS), 2022, pp. 12–17. doi: 10.1109/ICE3IS56585.2022.10010110.
D. N. K. Samudrala, “Cybersecurity Intrusion Detection Dataset,” Kaggle. [Online]. Available: https://www.kaggle.com/datasets/dnkumars/cybersecurity-intrusion-detection-dataset
Parjito, I. Ahmad, R. I. Borman, A. D. Alexander, and Y. Jusman, “Combining Extreme Learning Machine and Linear Discriminant Analysis for Optimized Apple Leaf Disease Classification,” in International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS), IEEE, 2024, pp. 138–143. doi: 10.1109/ICE3IS62977.2024.10775844.
K. Shah, S. Shah, V. Shah, and A. Godbole, “Optimization of Data Splitting Methods For Machine Learning,” in International Conference on Innovative Computing & Communication (ICICC), 2025. doi: https://dx.doi.org/10.2139/ssrn.5190348.
S. E. H. Yulianti, O. Soesanto, and Y. Sukmawaty, “Penerapan Metode Extreme Gradient Boosting (XGBoost) pada Klasifikasi Nasabah Kartu Kredit,” J. Math. Theory Appl., vol. 4, no. 1, pp. 21–26, 2022, doi: https://doi.org/10.31605/jomta.v4i1.1792.
I. Z. A. Illah, W. S. J. Sapu, and A. T. Damaliana, “Implementasi Metode Klasifikasi LightGBM dan Analisis Survival dalam Memprediksi Pelanggan Churn,” J. Komtika (Komputasi dan Inform., vol. 8, no. 1, pp. 43–53, 2024, doi: https://doi.org/10.31603/komtika.v8i1.11194.
Z. Abidin, R. I. Borman, F. B. Ananda, P. Prasetyawan, F. Rossi, and Y. Jusman, “Classification of Indonesian Traditional Snacks Based on Image Using Convolutional Neural Network (CNN) Algorithm,” in International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS), 2021, pp. 18–23. doi: 10.1109/ICE3IS54102.2021.9649707.
Y. Liu, Y. Li, and D. Xie, “Implications of imbalanced datasets for empirical ROC-AUC estimation in binary classification tasks,” J. Stat. Comput. Simul., vol. 94, no. 1, pp. 183–203, Jan. 2024, doi: 10.1080/00949655.2023.2238235.
T. Chen and R. C.-W. Wong, “Improving Representation Learning for Session-based Recommendation,” in IEEE International Conference on Big Data (Big Data), 2022, pp. 854–863. doi: 10.1109/BigData55660.2022.10020851.
D. T. Murdiansyah, “Prediksi Stroke Menggunakan Extreme Gradient Boosting,” JIKO (Jurnal Inform. dan Komputer), vol. 8, no. 2, p. 419, 2024, doi: 10.26798/jiko.v8i2.1295.
D. R. Arrayyan, R. G. Guntara, and M. R. Nugraha, “Deteksi Komentar Spam Judi Online Berbahasa Indonesia Menggunakan XGBoost dan TF-IDF,” J. Algoritm., vol. 22, no. 2, pp. 2066–2075, 2025, doi: 10.33364/algoritma/v.22-2.3012.
N. I. Sulistiyani, R. A. Purnomo, N. Rohmatunisa, R. M. Pujo, R. B. Bahaweres, and N. Hakiem, “Prediksi Jenis Kebocoran Data Kesehatan di AS Berdasarkan Laporan HIPAA Menggunakan LightGBM dan Kerangka OSEMN,” INDEXIA Inform. Comput. Intell. J., vol. 07, no. 02, pp. 110–119, 2025, doi: https://doi.org/10.30587/indexia.v7i2.10220.
S. Y. Nailendra, W. Witanti, and G. Abdillah, “Optimasi Prediksi Penjualan Retail Online Menggunakan LightGBM dan Hyperparameter Tuning,” J. Algoritm., vol. 22, no. 2, pp. 1931–1942, 2025, doi: 10.33364/algoritma/v.22-2.2551.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Deteksi Intrusi Jaringan Berbasis Machine Learning Menggunakan Model Boosting dengan Session-Level Feature Representation
Pages: 489-498
Copyright (c) 2026 Mochamad Sanwasih, Fajar Septian, Ristasari Dwi Septiana
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
