DETEKSI FRAMEWORK HYBRID INTRUSION DETECTION SYSTEM (IDS) DUA TAHAP BERBASIS DECISION TREE DAN ENSEMBLE LEARNING UNTUK EFISIENSI KOMPUTASI
DOI:
https://doi.org/10.35145/joisie.v10i1.5873Kata Kunci:
Deteksi Serangan, Deteksi Hibrida, Pembelajaran Ensemble, Pohon Keputusan, XGBoostAbstrak
Penelitian ini mengusulkan framework deteksi serangan siber hybrid dengan menggabungkan rule based filtering dan machine learning dalam proses dua tahap. Pada tahap pertama, algoritma Decision Tree digunakan untuk ekstraksi aturan yang dapat diinterpretasikan, diikuti oleh klasifikasi menggunakan algoritma ensemble, yaitu Random Forest, XGBoost, dan LightGBM. Framework dievaluasi menggunakan dataset UNSW-NB15, yang terdiri dari 2.540.044 data normal dan serangan dari sembilan tipe serangan. Filtering berbasis aturan menghapus 23% data non-serangan, sehingga 77% data tersisa untuk klasifikasi. Efisiensi komputasi diukur dengan membandingkan waktu eksekusi dan penggunaan CPU dengan dan tanpa filtering. Dengan filtering, program berjalan selama 9 menit dengan penggunaan CPU maksimum 0–303%, menghasilkan pengurangan waktu pemrosesan sebesar 24% dibandingkan tanpa filtering. Hasil penelitian menunjukkan XGBoost memberikan performa terbaik dengan akurasi 96,1%, recall 95,0%, dan F1-score 95,2%. Framework juga mengoptimalkan recall untuk meminimalkan false negative, dan meningkatkan recall dan mencapai 97.0% pada model XGBoost. Validasi statistik menggunakan uji Wilcoxon menunjukkan peningkatan performa signifikan (p < 0,05). Framework hybrid ini tidak hanya meningkatkan akurasi dan efisiensi, tetapi juga memberikan sistem deteksi yang interpretatif dan transparan, sehingga cocok untuk implementasi Intrusion Detection System (IDS) real-time.
Unduhan
Referensi
Abdallah, E.E. and Otoom, A.F. (2022) “Intrusion detection systems using supervised machine learning techniques: a survey,” Procedia Computer Science, 201, pp. 205–212. https://doi.org/10.1016/j.procs.2022.03.029
Akgun, D., Hizal, S. and Cavusoglu, U. (2022) “A new DDoS attacks intrusion detection model based on deep learning for cybersecurity,” Computers & Security, 118, p. 102748. https://doi.org/10.1016/j.cose.2022.102748
Abdallah, E.E. and Otoom, A.F. (2022) “Intrusion detection systems using supervised machine learning techniques: a survey,” Procedia Computer Science, 201, pp. 205–212. https://doi.org/10.1016/j.procs.2022.03.029
Almuhanna, R. and Dardouri, S. (2025) “A deep learning/machine learning approach for anomaly based network intrusion detection,” Frontiers in Artificial Intelligence, 8, 1625891. doi: 10.3389/frai.2025.1625891. https://doi.org/10.3389/frai.2025.1625891
Azizi Doost, P., Sarhani Moghadam, S., Khezri, E., Basem, A. and Trik, M. (2025) “A new intrusion detection method using ensemble classification and feature selection,” Scientific Reports, 15(1). doi: 10.1038/s41598-025-98604-w. https://doi.org/10.1038/s41598-025-98604-w
Akgun, D., Hizal, S. and Cavusoglu, U. (2022) “A new DDoS attacks intrusion detection model based on deep learning for cybersecurity,” Computers & Security, 118, p. 102748. https://doi.org/10.1016/j.cose.2022.102748
Dewangan, L. and Sharma, S. (2025) “Deep Learning-based Intrusion Detection Systems: Enhancing Cyber Defense Mechanisms,” 2025 International Conference on Innovations in Intelligent Systems: Advancements in Computing, Communication, and Cybersecurity (ISAC3). IEEE, pp. 1–5. https://doi.org/10.1109/ISAC364032.2025.11156515
Dighriri, A.A. and Chatrath, S. (2025) “Journal of Cybersecurity, Volume 5, Issue 4,” Journal of Cybersecurity, 5(4). https://doi.org/10.3390/jcp5040113
Geetha, R. and Thilagam, T. (2021) “A Review on the Effectiveness of Machine Learning and Deep Learning Algorithms for Cyber Security: R. Geetha, T. Thilagam,” Archives of Computational Methods in Engineering, 28(4), pp. 2861–2879. https://doi.org/10.1007/s11831-020-09478-2
Halbouni, A. et al. (2022) “Machine learning and deep learning approaches for cybersecurity: A review,” IEEE Access, 10, pp. 19572–19585. https://doi.org/10.1109/ACCESS.2022.3151248
Handa, A. and Semwal, P. (2022) “Evaluating performance of scalable fair clustering machine learning techniques in detecting cyber attacks in industrial control systems,” Handbook of Big Data Analytics and Forensics. Springer, pp. 105–116. https://doi.org/10.1007/978-3-030-74753-4_7
ji Song, E., Hong, S.-C. and Kang, A.R. (2026) “An Implementation of TF-IDF Feature Extraction and Machine Learning Based Web Attack Detection System,” Journal of The Korea Society of Computer and Information (????????????), 31(1), pp. 109–120. https://doi.org/10.9708/jksci.2026.31.01.109
Kilincer, I.F., Ertam, F. and Sengur, A. (2021) “Machine learning methods for cyber security intrusion detection: Datasets and comparative study,” Computer Networks, 188, p. 107840.
Kumar, S. (2025) “Transforming Cybersecurity with Agentic AI to Combat Emerging Threats,” Telecommunications Policy [Preprint]. https://doi.org/10.1016/j.comnet.2021.107840
Lallie, H.S. et al. (2025) “Analysing Cyber Attacks and Cyber Security Vulnerabilities in the University Sector,” Computers, 14(2), p. 49. https://doi.org/10.3390/computers14020049
Mohale, V.Z. and Obagbuwa, I.C. (2025) “A systematic review on the integration of explainable artificial intelligence in intrusion detection systems to enhancing transparency and interpretability in cybersecurity,” Frontiers in Artificial Intelligence, 8, 1526221. doi: 10.3389/frai.2025.1526221. https://doi.org/10.3389/frai.2025.1526221
Najem, D.F. and Kareem, S.M. (2025) “A Review on Cyber Security and Cyber Attacks,” Journal of Al-Qadisiyah for Computer Science and Mathematics, 17(2), pp. 153–161. https://doi.org/10.29304/jqcsm.2025.17.22195
Natasya, C., Irvin, I. and Gunawan, A.A.S. (2024) “A Systematic Literature Review: Cyber Attack: Phishing Environments, Techniques, and Detection Mechanism,” International Journal of Computer Science and Humanitarian AI, 1(1), pp. 7–11. https://doi.org/10.21512/ijcshai.v1i1.12155
Naureni, A., Nugraha, Y. and Aminanto, M.E. (2025) “Revisiting Cyber Threats in Government Sectors: A Systematic Review of Attacks, Challenges, and Policy-Level Defenses,” International Journal of Advances in Data and Information Systems, 6(2), pp. 447–459. https://doi.org/10.59395/ijadis.v6i2.1404
Susanto, N. (2025) “Gated Recurrent Unit with Self-Attention for Sentiment Analysis of Amazon Kindle Store Reviews” JURNAL INFORMATIKA UNIVERSITAS PAMULANG Vol. 10 No. 4
Pinto, A., Herrera, L.-C., Donoso, Y. and Gutierrez, J.A. (2023) “Survey on Intrusion Detection Systems Based on Machine Learning Techniques for the Protection of Critical Infrastructure,” Sensors, 23(5), 2415. doi: 10.3390/s23052415. https://doi.org/10.3390/s23052415
Shi, Y. et al. (2024) “Autonomous Cyber Defense using Graph Attention Network Enhanced Reinforcement Learning,” 2024 IEEE 30th International Conference on Parallel and Distributed Systems (ICPADS). IEEE, pp. 568–577. https://doi.org/10.1109/ICPADS63350.2024.00080
Sun, J. et al. (2024) “Research on Deep Learning of Convolutional Neural Network for Action Recognition of Intelligent Terminals in the Big Data Environment and its Intelligent Software Application,” 2024 IEEE 7th International Conference on Automation, Electronics and Electrical Engineering (AUTEEE). IEEE, pp. 996–1004. https://doi.org/10.1109/AUTEEE62881.2024.10869734
Wang, Y., Han, D. and Cui, M. (2023) “Intrusion detection model of internet of things based on deep learning,” Computer Science and Information Systems, 20(4), pp. 1519–1540. https://doi.org/10.2298/CSIS230418058W
Zhang, X. et al. (2023) “An automatic and efficient malware traffic classification method for secure Internet of Things,” IEEE Internet of Things Journal, 11(5), pp. 8448–8458. https://doi.org/10.1109/JIOT.2023.3318290
Unduhan
Diterbitkan
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2026 JOISIE (Journal Of Information Systems And Informatics Engineering)
Artikel ini berlisensiCreative Commons Attribution-ShareAlike 4.0 International License.
