Perbandingan Performa Algoritma Random Forest dan SVM Dalam Mendeteksi serangan DDoS di Jaringan Cloud

Muhammad Andika Fathurrahman; Dwi Wahyu Prabowo

doi:10.30595/jrre.v7i2.27866

Authors

Muhammad Andika Fathurrahman Universitas Darwan Ali
Dwi Wahyu Prabowo Universitas Darwan Ali

DOI:

https://doi.org/10.30595/jrre.v7i2.27866

Keywords:

DDoS, Machine Learning, Random Forest, Seleksi Fitur, CFS

Abstract

Distributed Denial of Service (DDoS) merupakan ancaman serius terhadap layanan jaringan, khususnya pada lingkungan cloud yang bersifat terbuka dan dinamis. Penelitian ini bertujuan untuk mendeteksi serangan DDoS menggunakan algoritma machine learning, yakni Random Forest (RF) dan Support Vector Machine (SVM), serta mengevaluasi pengaruh seleksi fitur menggunakan Correlation-based Feature Selection (CFS) dan Rough Set (RS). Eksperimen dilakukan menggunakan dataset dari Zenodo dengan validasi silang 10-Fold dan evaluasi berbasis metrik accuracy, precision, recall, F1-score, dan kappa. Hasil menunjukkan bahwa model Random Forest secara konsisten memberikan performa terbaik dibandingkan SVM. Skema terbaik yaitu Random Forest dengan seleksi fitur RS menghasilkan nilai accuracy 99.99%, precision 100%, recall 99.99%, F1-score 99.99%, dan kappa score 99.98%, yang menunjukkan efektivitas tinggi dalam mendeteksi serangan DDoS secara akurat dan andal.

References

[1] P. Bintoro, Ratnasari, E. Wihardjo, I. P. Putri dan A. Asari, Pengantar Machine Learning, Kota Solok, Sumatera Barat: PT MAFY MEDIA LITERASI INDONESIA, September 2024.

[2] T. Aytaç, M. A. Aydın dan A. H. Zaim, “Detection DDOS Attacks Using Machine Learning Methods,” Electrica, vol. 20, pp. 159-167, 2020.

[3] S. Budiman, A. Sunyoto dan A. Nasiri, “Analisa Performa Penggunaan Feature Selection untuk Mendeteksi Intrusion Detection Systems dengan Algoritma Random Forest Classifier,” SISTEMASI, vol. 10, p. 753, 2021.

[4] M. Kuhn dan K. Johnson, Applied Predictive Modeling, New York: Springer, 2013.

[5] D. G. Altman, Practical Statistics for Medical Research, London: Chapman and Hall/CRC, 1991.

[6] R. Amrish, “DDoS Detection using Machine Learning Techniques,” Journal of IoT in Social, Mobile, Analytics, and Cloud, vol. 4, no. 1, pp. 24-32, 2022.

[7] Attou, Hanaa dan Azidine, “Cloud-Based Intrusion Detection Approach Using Machine Learning Techniques,” Big Data Mining and Analytics, vol. 6, pp. 311-320, 2023.

[8] Beer, F. Buhler dan Ulrich, “Feature selection for flow-based intrusion detection using Rough Set Theory,” IEEE Explore, pp. 617-624, 2017.

[9] Whitney dan Mann, “On a Test of Whether One of Two Random Variables is Stochastically Larger than the Other,” Annals of Mathematical Statistics, vol. 18, pp. 50-60, 1974.

[10] F. Chollet, Deep Learning with Python, Manning Publications, 2021.

[11] V. Jayaswal, “Performance Metrics: Confusion matrix, Precision, Recall, and F1 Score,” Towards Data Science, 14 September 2020. [Online]. Available: https://towardsdatascience.com/performance-metrics-confusion-matrix-precision-recall-and-f1-score-a8fe076a2262/. [Diakses 19 Agustus 2025].

[12] M. Fadli dan R. A. Saputra, “KLASIFIKASI DAN EVALUASI PERFORMA MODEL RANDOM FOREST UNTUK PREDIKSI STROKE,” Jurnal Teknik, vol. 12, no. 2, pp. 72-80, 2023.

[13] Amorim, A. Fernandez dan Delgado, “Do we need hundreds of classifiers to solve real world classification problems?,” Journal of Machine Learning Research, vol. 15, pp. 3133-3181, 2014.

[14] J. V. Ade dan A. V. Deorankar, “Ensemble Learning Methods for DDoS Attack Detection,” International Journal of Science and Engineering Applications, vol. 13, no. 05, pp. 40-45, 2024.

[15] R. Gunawan, E. S. Handika dan E. Ismanto, “Pendekatan Machine Learning Dengan Menggunakan Algoritma Xgboost (ExtremeGradient Boosting) Untuk Peningkatan Kinerja Klasifikasi Serangan Syn,” Jurnal Computer Science and Information Technology (CoSciTech), vol. 3 No 3, pp. 453-463, Desember 2022.