Journals / Bilişim Teknolojileri Dergisi / 2026 / Cilt: 19 Sayı: 3

Explainable XGBoost-Based Detection of IoT DDoS Attacks Using SHAP Analysis

SHAP Analizi ile Açıklanabilir XGBoost Tabanlı IoT DDoS Saldırı Tespiti

Mustafa Yeniad(ANKARA YILDIRIM BEYAZIT UNIVERSITY, FACULTY OF ENGINEERING AND NATURAL SCIENCES)0000-0002-9422-4974
Abdel-Hamid Abdelkerim Mahamat(ANKARA YILDIRIM BEYAZIT ÜNİVERSİTESİ)0009-0004-8947-8277
Pages
353–362
Publication Date
2026-07-31
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Overall, this study shows that integrating tree-based machine learning with explainable artificial intelligence can significantly improve both the effectiveness and transparency of intrusion detection systems.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The rapid growth of Internet of Things (IoT) networks, accelerated by 5G technologies, has expanded the attack surface and increased vulnerability to Distributed Denial-of-Service (DDoS) attacks.
📊
Key Findings & Data:Although machine learning techniques have demonstrated strong detection performance, many intrusion detection systems operate as black-box models, limiting their transparency.
💡
Conclusion & Impact:Overall, this study shows that integrating tree-based machine learning with explainable artificial intelligence can significantly improve both the effectiveness and transparency of intrusion detection systems.
🔬Design:Modeling & Simulation
📍Scope:2023 Verileri
⚙️Variables:dağıtıılmış hizmet engelleme (DDoS) · saldırı tespit sistemleri (IDS) · XGBoost

Abstract

The rapid growth of Internet of Things (IoT) networks, accelerated by 5G technologies, has expanded the attack surface and increased vulnerability to Distributed Denial-of-Service (DDoS) attacks. Although machine learning techniques have demonstrated strong detection performance, many intrusion detection systems operate as black-box models, limiting their transparency. To address this limitation, this study proposes an explainable intrusion detection framework based on XGBoost integrated with SHapley Additive exPlanations (SHAP). Evaluated on the ACI-IoT-2023 dataset for binary classification of benign and DDoS traffic, the proposed framework demonstrated high detection performance, achieving 99.93% accuracy and 99.94% F1-score while maintaining a low inference time suitable for real-time intrusion detection. Beyond performance evaluation, explainability analysis was conducted using global and local SHAP analyses, statistical feature behavior analysis, misclassification analysis, and synthetic feature-based validation. The results reveal that temporal traffic characteristics, particularly Idle Max and Flow IAT Min, together with protocol-related behavior, represent the most influential factors in distinguishing malicious from benign traffic. The findings further demonstrate that the proposed framework learns stable and interpretable traffic patterns rather than relying on isolated feature values or arbitrary statistical correlations. Overall, this study shows that integrating tree-based machine learning with explainable artificial intelligence can significantly improve both the effectiveness and transparency of intrusion detection systems.

Özet

Nesnelerin İnterneti (IoT) ağlarının hızlı büyümesi ve 5G teknolojilerinin yaygınlaşması, saldırı yüzeyini genişletmiş ve Dağıtılmış Hizmet Engelleme (DDoS) saldırılarına karşı savunmasızlığı artırmıştır. Makine öğrenmesi teknikleri yüksek saldırı tespit performansı göstermesine rağmen, birçok saldırı tespit sistemi kara kutu modeller olarak çalışmakta ve bu durum şeffaflığı sınırlandırmaktadır. Bu sınırlamayı gidermek amacıyla, bu çalışmada XGBoost ile SHapley Additive exPlanations (SHAP) yöntemini bütünleştiren açıklanabilir bir saldırı tespit çerçevesi önerilmiştir. Önerilen çerçeve, normal ağ trafiği ile DDoS saldırılarını ayırt eden ikili sınıflandırma yaklaşımı kullanılarak ACI-IoT-2023 veri kümesi üzerinde değerlendirilmiştir. Deneysel sonuçlar, önerilen modelin gerçek zamanlı saldırı tespit uygulamaları için uygun düşük çıkarım süresini korurken %99,93 doğruluk ve %99,94 F1-skoru ile yüksek tespit performansı sağladığını göstermektedir. Performans değerlendirmesinin yanı sıra, global ve yerel SHAP analizleri, istatistiksel özellik davranış analizi, yanlış sınıflandırma analizi ve sentetik özellik tabanlı doğrulama yöntemleri kullanılarak açıklanabilirlik analizi gerçekleştirilmiştir. Bulgular, özellikle Idle Max ve Flow IAT Min gibi zamansal trafik özelliklerinin, protokol tabanlı davranışlarla birlikte, kötü amaçlı ve normal trafiğin ayırt edilmesinde en etkili faktörler olduğunu göstermektedir. Sonuçlar ayrıca önerilen çerçevenin, belirli özellik değerlerine veya rastgele istatistiksel ilişkilere dayanmak yerine, kararlı ve yorumlanabilir davranışsal ilişkiler öğrendiğini ortaya koymaktadır. Genel olarak bu çalışma, ağaç tabanlı makine öğrenmesi yöntemlerinin açıklanabilir yapay zekâ ile bütünleştirilmesinin saldırı tespit sistemlerinin hem etkinliğini hem de şeffaflığını önemli ölçüde artırabileceğini göstermektedir.

🔖

Cite This Article

Yeniad, M., Mahamat, A. A. (2026). Explainable XGBoost-Based Detection of IoT DDoS Attacks Using SHAP Analysis. Bilişim Teknolojileri Dergisi, Cilt: 19 Sayı: 3, 353–362. https://doi.org/10.17671/gazibtd.1961325

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (18)

  1. Ericsson, Ericsson mobility report november 2025, Sweden, https://www.ericsson.com/4aca6f/assets/local/reports-papers/mobility-report/documents/2025/ericsson-mobility-report-november-2025.pdf, 12.05.2025.
  2. R. A. Paskauskas, “ENISA: 5G design and architecture of global mobile networks; threats, risks, vulnerabilities; cybersecurity considerations”, Open Research Europe, 2, 125, 2023.
  3. A.-H. A. Mahamat and O. Karal, “Efficient Detection of IoT-Based DDoS Attacks Using Machine Learning Models”, 2025 Innovations in Intelligent Systems and Applications Conference (ASYU), Bursa, Türkiye, 1-6, Sep 10, 2025.
  4. D. Minh, H. X. Wang, Y. F. Li, and T. N. Nguyen, “Explainable artificial intelligence: a comprehensive review”, Artificial Intelligence Review, 55(5), 3503–3568, 2022.
  5. S. K. Jagatheesaperumal, Q. V. Pham, R. Ruby, Z. Yang, C. Xu, and Z. Zhang, “Explainable AI Over the Internet of Things (IoT): Overview, State-of-the-Art and Future Directions,”, IEEE Open Journal of the Communications Society, 3, 2106–2136, 2022.
  6. J. Dong, H. Chen, S. Shen, H. Xu, and Z. Liu, “Interpretable intrusion detection for IoT security: A SHAP-enhanced NGBoost model”, Computer Networks, 275, 111937, 2025.
  7. S. Bellegdi, A. Selamat, S. O. Olatunji, H. Fujita, and O. Krejcar, “Explainable Machine Learning for Intrusion Detection,”, International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, 14748, 122–134, 2024.
  8. M. Wang, K. Zheng, Y. Yang, and X. Wang, “An Explainable Machine Learning Framework for Intrusion Detection Systems”, IEEE access, 8, 73127–73141, 2020.
  9. S. Mane and D. Rao, “Explaining Network Intrusion Detection System Using Explainable AI Framework”, arXiv preprint, https://arxiv.org/pdf/2103.07110, 2021.
  10. I. A. Khan, N. Moustafa, D. Pi, K. M. Sallam, A. Y. Zomaya, and B. Li, “A New Explainable Deep Learning Framework for Cyber Threat Discovery in Industrial IoT Networks”, IEEE Internet of Things Journal, 9 (13), 11604–11613, 2021.
  11. Z. A. El Houda, B. Brik, and L. Khoukhi, “‘Why Should I Trust Your IDS?’: An Explainable Deep Learning Framework for Intrusion Detection Systems in Internet of Things Networks”, IEEE Open Journal of the Communications Society, 3, 1164–1176, 2022.
  12. Y. Hosain and M. Çakmak, “XAI-XGBoost: an innovative explainable intrusion detection approach for securing internet of medical things systems”, Scientific Reports, 15(1), 22278, 2025.
  13. Ashikuzzaman, M. S. Hossain, J. A. Joy, M. Z. Akon, M. M. Ahmed and M. N. Islam, “An Optimized Decision Tree-Based Framework for Explainable IoT Anomaly Detection”, 2025 IEEE 2nd International Conference on Computing, Applications and Systems (COMPAS), Kushtia, Bangladesh, 1-7, Oct 23, 2025.
  14. E. A. Nack, M. C. McKenzie, and N. D. Bastian, “ACI-IoT-2023: A Robust Dataset for Internet of Things Network Security Analysis”, Military Communications Conference (MILCOM), Washington DC, USA, 1-6, Oct 28, 2024.
  15. T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system”, ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794, 2016.
  16. S. M. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions”, 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, 30, 2017.
  17. S. M. Lundberg, G. G. Erion, and S.-I. Lee, “Consistent Individualized Feature Attribution for Tree Ensembles”, arXiv preprint, https://arxiv.org/pdf/1802.03888, 2018.
  18. M. A. M.Yusof, F. H. M. Ali, and M. Y. Darus, “Detection and Defense Algorithms of Different Types of DDoS Attacks”, International Conference on Computational Science and Technology, Singapore, 488, 370–379, 2018.