Perbandingan Kinerja CD-KNN Dalam Klasifikasi Serangan Ddos UDP Flood
Abstract
Keamanan siber menjadi isu kritis di era digital, terutama serangan Distributed Denial of Service (DDoS) UDP Flood yang meningkat signifikan hingga 59,31% pada tahun 2023. Penelitian ini mengimplementasikan algoritma Cluster-based Dynamic K-Nearest Neighbor (CD-KNN) dengan parameter α = 6, yang diperkuat dengan seleksi fitur Analysis of Variance (ANOVA) dan teknik penyeimbangan data Synthetic Minority Oversampling Technique (SMOTE) untuk mendeteksi serangan DDoS UDP Flood berbasis anomali lalu lintas jaringan. Dataset CICDDoS2019 diproses melalui tahapan preprocessing menyeluruh, termasuk penghapusan 20 fitur tidak relevan, normalisasi Min-Max, dan penyeimbangan distribusi kelas. Evaluasi dilakukan pada dua skenario: CD-KNN dengan ANOVA dan CD-KNN dengan ANOVA-SMOTE. Hasil eksperimen menunjukkan bahwa model CD-KNN dengan ANOVA-SMOTE menghasilkan performa terbaik dengan akurasi 99.994%, presisi 99.998%, recall 99.996%, dan F1-score 99.997%. Penerapan SMOTE meningkatkan recall kelas minoritas sebesar 2,47% dibandingkan model tanpa SMOTE, dengan waktu komputasi 3903 detik yang tetap efisien untuk dataset berskala besar. Temuan ini menunjukkan bahwa kombinasi CD-KNN, ANOVA, dan SMOTE merupakan pendekatan komprehensif yang efektif dalam sistem deteksi intrusi berbasis anomali untuk serangan DDoS UDP Flood.
References
Alassaf, M., & Qamar, A. M. (2022). Improving Sentiment Analysis Of Arabic Tweets By One-Way ANOVA. Journal of King Saud University - Computer and Information Sciences, 34(6), 2849–2859. https://doi.org/10.1016/j.jksuci.2020.10.023
Chandrashekar, G., & Sahin, F. (2014). A Survey On Feature Selection Methods. Computers and Electrical Engineering, 40(1), 16–28. https://doi.org/10.1016/j.compeleceng.2013.11.024
Chawla, N. V, Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic Minority Over-sampling Technique. In Journal of Artificial Intelligence Research (Vol. 16).
Elreedy, D., Atiya, A. F., & Kamalov, F. (2024). A Theoretical Distribution Analysis Of Synthetic Minority Oversampling Technique (SMOTE) For Imbalanced Learning. Machine Learning, 113(7), 4903–4923. https://doi.org/10.1007/s10994-022-06296-4
Heydarian, M., Doyle, T. E., & Samavi, R. (2022). MLCM: Multi-Label Confusion Matrix. IEEE Access, 10, 19083–19095. https://doi.org/10.1109/ACCESS.2022.3151048
Joloudari, J. H., Marefat, A., Nematollahi, M. A., Oyelere, S. S., & Hussain, S. (2023). Effective Class-Imbalance Learning Based On SMOTE And Convolutional Neural Networks. Applied Sciences (Switzerland), 13(6). https://doi.org/10.3390/app13064006
Kumar, M., Rath, N. K., Swain, A., & Rath, S. K. (2015). Feature Selection And Classification Of Microarray Data Using Mapreduce Based ANOVA And K-Nearest Neighbor. Procedia Computer Science, 54, 301–310. https://doi.org/10.1016/j.procs.2015.06.035
Markoulidakis, I., Rallis, I., Georgoulas, I., Kopsiaftis, G., Doulamis, A., & Doulamis, N. (2021). Multiclass Confusion Matrix Reduction Method And Its Application On Net Promoter Score Classification Problem. Technologies, 9(4). https://doi.org/10.3390/technologies9040081
Megantara, A. A., & Ahmad, T. (2020). Feature Importance Ranking For Increasing Performance Of Intrusion Detection System. 2020 3rd International Conference on Computer and Informatics Engineering, IC2IE 2020, 37–42. https://doi.org/10.1109/IC2IE50715.2020.9274570
Muraina, I. O. (2022). Ideal Dataset Splitting Ratios In Machine Learning Algorithms: General Concerns For Data Scientists And Data Analysts. https://www.researchgate.net/publication/358284895
Musthafa, M. B., Huda, S., Kodera, Y., Ali, M. A., Araki, S., Mwaura, J., & Nogami, Y. (2024). Optimizing IoT Intrusion Detection Using Balanced Class Distribution, Feature Selection, And Ensemble Machine Learning Techniques. Sensors, 24(13). https://doi.org/10.3390/s24134293
Qrator Labs. (2024). Q3 2024 DDoS, Bots and BGP Incidents Statistics and Overview.
Rácz, A., Bajusz, D., & Héberger, K. (2021). Effect Of Dataset Size And Train/Test Split Ratios In Qsar/Qspr Multiclass Classification. Molecules, 26(4). https://doi.org/10.3390/molecules26041111
Ramli, N. E., Yahya, Z. R., & Said, N. A. (2022). Confusion Matrix As Performance Measure For Corner Detectors. Journal of Advanced Research in Applied Sciences and Engineering Technology, 29(1), 256–265. https://doi.org/10.37934/araset.29.1.256265
Robindro, K., Singh, Y. R., Clinton, U. B., Takhellambam, L., & Hoque, N. (2022). CD-KNN: A Modified K-Nearest Neighbor Classifier With Dynamic K Value. Lecture Notes in Electrical Engineering, 925, 753–762. https://doi.org/10.1007/978-981-19-4831-2_62
Salmi, S., & Oughdir, L. (2023). Performance Evaluation Of Deep Learning Techniques For Dos Attacks Detection In Wireless Sensor Network. Journal of Big Data, 10(1). https://doi.org/10.1186/s40537-023-00692-w
Sharafaldin, I., Lashkari, A. H., Hakak, S., & Ghorbani, A. A. (2019). Developing Realistic Distributed Denial Of Service (Ddos) Attack Dataset And Taxonomy. IEEE.
SOC Radar. (2024). Indonesia Threat Landscape Report.
Varoquaux, G., & Colliot, O. (2023). Evaluating Machine Learning Models And Their Diagnostic Value. In Neuromethods (Vol. 197, pp. 601–630). Humana Press Inc. https://doi.org/10.1007/978-1-0716-3195-9_20
Wang, S., Dai, Y., Shen, J., & Xuan, J. (2021). Research On Expansion And Classification Of Imbalanced Data Based On SMOTE Algorithm. Scientific Reports, 11(1). https://doi.org/10.1038/s41598-021-03430-5
Full Text: PDF