Optimasi Sistem Deteksi Intrusi Berbasis Deep Neural Network dengan Seleksi Fitur Adaptif pada Jaringan Komputer Modern
DOI:
https://doi.org/10.61722/jmia.v3i2.9425Keywords:
Deep Neural Network, Jaringan Komputer, Keamanan Jaringan, Seleksi Fitur Adaptif, Sistem Deteksi IntrusiAbstract
Meningkatnya kompleksitas dan kecanggihan ancaman siber pada jaringan komputer modern mendorong kebutuhan akan Sistem Deteksi Intrusi (IDS) yang lebih cerdas dan adaptif. Penelitian ini mengusulkan optimasi Sistem Deteksi Intrusi berbasis Deep Neural Network (DNN) yang dikombinasikan dengan mekanisme Seleksi Fitur Adaptif untuk meningkatkan akurasi deteksi sekaligus mengurangi kompleksitas komputasi. Penelitian menggunakan dataset benchmark CICIDS-2017 dan NSL-KDD, menerapkan pendekatan seleksi fitur hibrida yang mengintegrasikan metode filter (mutual information dan chi-square) dengan metode wrapper (recursive feature elimination) untuk memilih subset fitur paling diskriminatif. Arsitektur DNN yang diusulkan terdiri dari beberapa hidden layer dengan batch normalization dan dropout regularization untuk mencegah overfitting. Hasil eksperimen menunjukkan bahwa sistem yang diusulkan mencapai akurasi deteksi 99,41%, presisi 98,87%, recall 99,12%, dan F1-score 98,99% pada dataset CICIDS-2017, melampaui metode yang ada. Metode seleksi fitur adaptif secara efektif mengurangi dimensi fitur sebesar 62,3%, menghasilkan pengurangan waktu pelatihan sebesar 45,7% tanpa mengorbankan kinerja deteksi. Sistem menunjukkan kinerja yang tangguh terhadap serangan zero-day dan lalu lintas terenkripsi. Temuan ini mengonfirmasi bahwa integrasi deep learning dengan seleksi fitur adaptif merupakan strategi efektif untuk membangun sistem deteksi intrusi generasi berikutnya pada lingkungan jaringan komputer modern.
References
Aldweesh, A., Derhab, A., & Emam, A. Z. (2020). Deep learning approaches for anomaly-based intrusion detection systems: A survey, taxonomy, and prospective outlook. Computers & Security, 90, 101681. https://www.sciencedirect.com/science/article/pii/S0167404819302226
Basnet, R. B., Shash, R., Johnson, C., Walgren, L., & Doleck, T. (2021). Towards detecting and classifying network intrusion traffic using deep learning frameworks. Journal of Internet Services and Information Security, 11(4), 1–17. https://jisis.org/issues/volume-11-no-4-november-2021/
Ferrag, M. A., Maglaras, L., Moschoyiannis, S., & Janicke, H. (2022). Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study. Journal of Information Security and Applications, 64, 103089. https://www.sciencedirect.com/science/article/pii/S2214212621002520
Gao, X., Shan, C., Hu, C., Niu, Z., & Liu, Z. (2022). An adaptive ensemble machine learning model for intrusion detection. IEEE Access, 7, 82512–82521. https://ieeexplore.ieee.org/document/8737505
Kasongo, S. M., & Sun, Y. (2022). A deep learning method with filter based feature engineering for wireless intrusion detection system. IEEE Access, 7, 38597–38607. https://ieeexplore.ieee.org/document/8668564
Khraisat, A., Gondal, I., Vamplew, P., & Kamruzzaman, J. (2019). Survey of intrusion detection systems: techniques, datasets and challenges. Cybersecurity, 2(1), 20. https://cybersecurity.springeropen.com/articles/10.1186/s42400-019-0038-7
Lansky, J., Ali, S., Mohammadi, M., Majeed, M. K., Karim, S. H., Rashidi, S., Hosseinzadeh, M., & Rahmani, A. M. (2021). Deep learning-based intrusion detection systems: A systematic review. IEEE Access, 9, 101574–101599. https://ieeexplore.ieee.org/document/9487003
Liao, H. J., Lin, C. H. R., Lin, Y. C., & Tung, K. Y. (2021). Intrusion detection system: A comprehensive review. Journal of Network and Computer Applications, 36(1), 16–24. https://www.sciencedirect.com/science/article/pii/S1084804512001343
Liu, H., Lang, B., Liu, M., & Yan, H. (2023). CNN and RNN based payload classification methods for attack detection. Knowledge-Based Systems, 163, 332–341. https://www.sciencedirect.com/science/article/pii/S0950705118304039
Roshan, S., & Zafar, A. (2021). Using overall accuracy and a confusion matrix to measure the performance of machine learning classification algorithms on network traffic data. International Journal of Computer Science and Mobile Computing, 10(9), 14–21. https://ijcsmc.com/docs/papers/September2021/V10I9202103.pdf
Sarhan, M., Layeghy, S., Moustafa, N., & Portmann, M. (2021). NetFlow datasets for machine learning-based network intrusion detection systems. In Big Data Technologies and Applications (pp. 117–135). Springer. https://link.springer.com/chapter/10.1007/978-3-030-72802-1_9
Shafiq, M., Tian, Z., Bashir, A. K., Du, X., & Guizani, M. (2022). CorrAUC: A malicious bot-IoT traffic detection method in IoT network using machine learning techniques. IEEE Internet of Things Journal, 8(5), 3242–3254. https://ieeexplore.ieee.org/document/9124779
Sharafaldin, I., Lashkari, A. H., & Ghorbani, A. A. (2018). Toward generating a new intrusion detection dataset and intrusion traffic characterization. In Proceedings of the 4th International Conference on Information Systems Security and Privacy (ICISSP) (pp. 108–116). SciTePress. https://www.scitepress.org/papers/2018/66398/66398.pdf
Thakkar, A., & Lohiya, R. (2021). A review of the advancement in intrusion detection datasets. Procedia Computer Science, 167, 636–645. https://www.sciencedirect.com/science/article/pii/S1877050920308292
Ullah, I., & Mahmoud, Q. H. (2021). A two-level flow-based anomalous activity detection system for IoT networks. Electronics, 9(3), 530. https://www.mdpi.com/2079-9292/9/3/530
Xu, C., Shen, J., Du, X., & Zhang, F. (2021). An intrusion detection system using a deep neural network with gated recurrent units. IEEE Access, 6, 48697–48707. https://ieeexplore.ieee.org/document/8455874
Zhang, H., Li, J. L., Liu, X. M., & Dong, C. (2023). Multi-dimensional feature fusion and stacking ensemble mechanism for network intrusion detection. Future Generation Computer Systems, 122, 130–143. https://www.sciencedirect.com/science/article/pii/S0167739X21001102
Downloads
Published
Issue
Section
License
Copyright (c) 2026 JURNAL MULTIDISIPLIN ILMU AKADEMIK
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
