PENERAPAN K-MEANS CLUSTERING UNTUK KLASIFIKASI POLA SERANGAN SIBERPADA INTRUSION DETECTION SYSTEM (IDS) BERBASIS DATA LOG JARINGAN
Keywords:
K-Means Clustering, Intrusion Detection System, Keamanan Jaringan, Klasifikasi Serangan SiberAbstract
Meningkatnya intensitas serangan siber secara global, termasuk di Indonesia yang mencatat 361 juta anomali trafik sepanjang Januari hingga Oktober 2023, mendorong kebutuhan mendesak terhadap sistem deteksi intrusi (IDS) yang mampu bekerja secara adaptif dan efisien. Penelitian ini menerapkan algoritma K-Means Clustering sebagai pendekatan unsupervised learning untuk mengklasifikasikan pola serangan siber meliputi DDoS, brute force, port scanning, botnet, dan web attack berdasarkan data log jaringan dari dataset CICIDS2017. Proses penelitian mencakup preprocessing data, reduksi fitur menggunakan Principal Component Analysis (PCA), penentuan jumlah kluster optimal dengan metode Elbow dan Silhouette Coefficient, serta evaluasi hasil clustering. Penelitian ini bertujuan menghasilkan model pengelompokan serangan yang dapat membantu tim keamanan jaringan dalam proses triase insiden secara lebih terstruktur tanpa ketergantungan pada data berlabel. Hasil evaluasi diharapkan menunjukkan nilai Silhouette Coefficient di atas 0,50 dengan pemisahan kluster yang jelas antara trafik normal dan trafik serangan.
Downloads
References
Ikotun, A. M., Ezugwu, A. E., Abualigah, L., et al. (2023). K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data. Information Sciences, 622, 178–210. https://doi.org/10.1016/j.ins.2022.11.139
Borikar, R. K., Sherekar, S. S., & Thakare, V. M. (2023). Intrusion Detection System based on K-means, Classification and Regression Trees Algorithm. International Journal of Scientific Research in Computer Science, Engineering and Information Technology.https://www.researchgate.net/publication/367942262
Emigawaty, E., Adi, K., & Rochim, A. (2023). K-Means Clustering Algorithm for Partitioning the Openness Levels of Open Government Data Portals. JOIV: International Journal on Informatics Visualization, 7(3). https://doi.org/10.30630/joiv.7.3.1761
Lin Yu, & Bai, Y. (2024). Design of network security monitoring system based on K-means clustering algorithm. International Journal on Information Technology.https://journals.sagepub.com/doi/10.3233/IDT-240185
Ghaffari et al. (2024). Enhancing intrusion detection in IoT: CNN integration with K-means for efficient and balanced classification. Expert Systems with Applications.https://www.sciencedirect.com/science/article/abs/pii/S0957417425037376
Fuzzy K-Means Clustering with Reconstructed Information (FKMRI). (2024). International Journal of Machine Learning and Cybernetics, Springer. https://doi.org/10.1007/s13042-024-02167-7
IndoSec Summit. (2024). The Escalating Cyber Threat in Indonesia: A Wake-Up Call for Digital Security. https://indosecsummit.com/the-escalating-cyber-threat-in-indonesia-a-wake-up-call-for-digital-security/
VIDA.id. (2024). Cyber Attack Trends in Indonesia. BSSN Annual Report Reference.
https://vida.id/en/blog/tren-serangan-siber-yang-banyak-terjadi-di-indonesia
StormWall. (2025). DDoS Trends and Statistics in APAC – 2024 Report. https://stormwall.network/resources/blog/ddos-trends-apac-2024
G2. (2025). 45+ DDoS Attack Statistics: Key Data and Takeaways for 2025. https://learn.g2.com/ddos-attack-statistics
Feng et al. (2024). Distributed K-Means Algorithm Based on a Spark Optimization Sample. PLOS ONE.https://doi.org/10.1371/journal.pone.0308993
StormWall. (2024). Q1 2024 DDoS Attack Report. https://stormwall.network/resources/blog/ddos-report-q1-2024
Tempo English. (2023). BSSN Records 361 Million Cyber Attacks in Indonesia.
https://en.tempo.co/read/1797753/bssn-records-361-million-cyber-attacks-in-indonesia
SOCRadar. (2024). Indonesia Threat Landscape Report 2024. https://socradar.io/wp-content/uploads/2024/08/SOCRadar-Indonesia-Threat-Landscape-Report-2024.pdf
SOCRadar. (2024). Global DDoS Attack Landscape: Insights from Q1 2024. https://socradar.io/global-ddos-attack-landscape-insights-from-q1-2024/
Help Net Security. (2024). DDoS attack power skyrockets to 1.6 Tbps.
https://www.helpnetsecurity.com/2024/02/02/ddos-attacks-h2-2023/
ResearchGate. (2023). Network Intrusion Detection: Comparative Analysis of NSL-KDD and CIC-IDS2017 Datasets. https://www.researchgate.net/publication/372926154
GitHub. (2023). Intrusion-Detection-CICIDS2017 – Detailed Feature Analysis. https://github.com/noushinpervez/Intrusion-Detection-CICIDS2017
Repository St. Cloud State University. (2022). A Supervised Machine Learning Approach to Network Intrusion Detection using CICIDS2017. https://repository.stcloudstate.edu/cgi/viewcontent.cgi?article=1155&context=msia_etds
Ikotun, A. M. et al. (2026). Performance Evaluation of Validity Indices on Evolutionary K-Means Clustering. ICONIP 2025, Springer.https://link.springer.com/chapter/10.1007/978-981-95-4384-7_23
Sharafaldin, I., Lashkari, A. H., & Ghorbani, A. A. (2018). Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization. ICISSP 2018.https://www.unb.ca/cic/datasets/ids-2017.html
ScienceDirect. (2025). A review on intrusion detection datasets: tools, processes, and features. https://www.sciencedirect.com/science/article/pii/S1389128625001458
PMC. (2024). Optimization of predictive performance of intrusion detection system using hybrid ensemble model. https://pmc.ncbi.nlm.nih.gov/articles/PMC10496009/
JISEM Journal. (2025). Hybrid Multi-Stage Intrusion Detection System (HMS-IDS) using CIC-ToN-IoT. https://jisem-journal.com/index.php/journal/article/download/1665/653/2705
Journal of Big Data, Springer. (2023). Network intrusion detection using data dimensions reduction techniques. https://journalofbigdata.springeropen.com/articles/10.1186/s40537-023-00697-5
MDPI Mathematics. (2021). Improved Constrained K-Means Algorithm for Clustering with Domain Knowledge. Mathematics, 9(19), 2390. https://www.mdpi.com/2227-7390/9/19/2390
MDPI Electronics. (2020). The K-Means Algorithm: A Comprehensive Survey and Performance Evaluation. Electronics, 9(8), 1295. https://www.mdpi.com/2079-9292/9/8/1295
MDPI Sustainability. (2022). K-Means Clustering Approach for Intelligent Customer Segmentation. Sustainability, 14(12), 7243. https://www.mdpi.com/2071-1050/14/12/7243
MDPI / PMC Future Internet. (2024). Insight into Anomaly Detection and Prediction Leveraging K-Means Clustering on Call Detail Records. https://pmc.ncbi.nlm.nih.gov/articles/PMC10974756/
PLOS ONE. (2025). Adoption of K-Means Clustering Algorithm in Smart City Security Analysis. PLOS ONE.https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0319620
MDPI Applied Sciences. (2021). K-Means-Based Nature-Inspired Metaheuristic Algorithms for Automatic Data Clustering. Applied Sciences, 11(23), 11246. https://www.mdpi.com/2076-3417/11/23/11246
Sinaga, K. P., & Yang, M. S. (2020). Unsupervised K-Means Clustering Algorithm. IEEE Access, 8. https://ieeexplore.ieee.org/document/9072123
Nature Scientific Reports. (2025). Enhancing Classification Accuracy in Medical Datasets Using a Hybrid Distance K-Means Method. Scientific Reports.https://www.nature.com/articles/s41598-025-30176-1
MDPI AI. (2024). Machine Learning-Based Network Anomaly Detection Using Clustering and Classification. AI, 5(4), 143. https://www.mdpi.com/2673-2688/5/4/143
PMC Computational Intelligence and Neuroscience. (2022). Research and Application of Clustering Algorithm for Text Big Data. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9200521/
MDPI Algorithms. (2025). Improving K-Means Clustering: Parallelized Variants for Satellite Image Clustering. Algorithms, 18(8), 532. https://www.mdpi.com/1999-4893/18/8/532
Downloads
Published
Issue
Section
License
Copyright (c) 2026 juwardi wafdan, muhammad suratman, kawet mujiono, muh. rasyid ridha (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
