Research Article

AutoGluon-Based Performance Analysis for Multi-Class Network Attack Detection

Volume: 13 Number: 2 December 24, 2025
TR EN

AutoGluon-Based Performance Analysis for Multi-Class Network Attack Detection

Abstract

The increasing complexity and critical nature of cyber threats have heightened the importance of effective attack detection systems. In this study, various machine learning algorithms (SVM, KNN, Logistic Regression, Random Forest, XGBoost), deep learning models (CNN, LSTM, DNN), and the AutoML-based AutoGluon framework are systematically compared for multi-class network attack detection. The experiments utilize the UNSW-NB15 dataset. Due to the imbalanced class distribution in the dataset, class balancing was applied in certain analyses using the SMOTE technique. All models were evaluated using commonly adopted classification metrics, including Accuracy, Precision, Recall, F1-score, and ROC-AUC. The findings indicate that AutoGluon achieved the highest performance, owing to its automated modeling and ensemble-based approach. These results suggest that automated modeling techniques may offer greater competitiveness and effectiveness compared to traditional methods. By systematically analyzing the performance of different modeling strategies in intrusion detection systems, this study aims to provide guidance for the development of future security solutions.

Keywords

References

  1. [1] Nour, M., Slay, J. UNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set). 2015 Military Communications and Information Systems Conference (MilCIS), IEEE, 2015.
  2. [2] Chawla, N. V., Bowyer, K. W., Hall, L. O., Kegelmeyer, W. P. SMOTE: Synthetic Minority Over-sampling Technique, Journal of Artificial Intelligence Research, 16, 321–357, 2002.
  3. [3] Fernández, A., García, S., Herrera, F., Chawla, N. V. SMOTE for learning from imbalanced data: progress and challenges, marking the 15-year anniversary. Journal of Artificial Intelligence Research. 61(1): 863–905, 2018.
  4. [4] Türkyılmaz, Y., Şentürk, A. Saldırı tespitinde makine öğrenmesi yöntemlerinin performans analizi. Avrupa Bilim ve Teknoloji Dergisi, (32), 107–112, 2021.
  5. [5] Şimşek, M. M., Atılgan, E. DoS and DDoS Attacks on Internet of Things and Their Detection by Machine Learning Algorithms. European Journal of Science and Technology, 32, 107–112, 2021.
  6. [6] Kurt Pehlivanoğlu, M., Kuyucu, A., Kaya, R., & Aydın, R. IoT Veri Kümelerinde Makine Öğrenmesine Dayalı Saldırı Tespiti. Avrupa Bilim ve Teknoloji Dergisi, 52, 19–26, 2023.
  7. [7] Ata, O., Kadhim, K. Network Intrusion Detection Using Machine Learning Techniques. Aurum Journal of Engineering Systems and Architecture, 2(1), 115–123, 2018.
  8. [8] Amarouche, S., Küçük, K. Machine and deep learning-based intrusion detection and comparison in Internet of Things. Journal of Naval Sciences and Engineering, 18(2), 333–361, 2022.

Details

Primary Language

English

Subjects

Information Security Management

Journal Section

Research Article

Early Pub Date

December 24, 2025

Publication Date

December 24, 2025

Submission Date

July 29, 2025

Acceptance Date

September 11, 2025

Published in Issue

Year 2025 Volume: 13 Number: 2

APA
Kocagöz, S., Yücalar, F., Borandag, E., & Şahinaslan, E. (2025). AutoGluon-Based Performance Analysis for Multi-Class Network Attack Detection. Mus Alparslan University Journal of Science, 13(2), 341-350. https://doi.org/10.18586/msufbd.1753107
AMA
1.Kocagöz S, Yücalar F, Borandag E, Şahinaslan E. AutoGluon-Based Performance Analysis for Multi-Class Network Attack Detection. Mus Alparslan University Journal of Science. 2025;13(2):341-350. doi:10.18586/msufbd.1753107
Chicago
Kocagöz, Sinan, Fatih Yücalar, Emin Borandag, and Ender Şahinaslan. 2025. “AutoGluon-Based Performance Analysis for Multi-Class Network Attack Detection”. Mus Alparslan University Journal of Science 13 (2): 341-50. https://doi.org/10.18586/msufbd.1753107.
EndNote
Kocagöz S, Yücalar F, Borandag E, Şahinaslan E (December 1, 2025) AutoGluon-Based Performance Analysis for Multi-Class Network Attack Detection. Mus Alparslan University Journal of Science 13 2 341–350.
IEEE
[1]S. Kocagöz, F. Yücalar, E. Borandag, and E. Şahinaslan, “AutoGluon-Based Performance Analysis for Multi-Class Network Attack Detection”, Mus Alparslan University Journal of Science, vol. 13, no. 2, pp. 341–350, Dec. 2025, doi: 10.18586/msufbd.1753107.
ISNAD
Kocagöz, Sinan - Yücalar, Fatih - Borandag, Emin - Şahinaslan, Ender. “AutoGluon-Based Performance Analysis for Multi-Class Network Attack Detection”. Mus Alparslan University Journal of Science 13/2 (December 1, 2025): 341-350. https://doi.org/10.18586/msufbd.1753107.
JAMA
1.Kocagöz S, Yücalar F, Borandag E, Şahinaslan E. AutoGluon-Based Performance Analysis for Multi-Class Network Attack Detection. Mus Alparslan University Journal of Science. 2025;13:341–350.
MLA
Kocagöz, Sinan, et al. “AutoGluon-Based Performance Analysis for Multi-Class Network Attack Detection”. Mus Alparslan University Journal of Science, vol. 13, no. 2, Dec. 2025, pp. 341-50, doi:10.18586/msufbd.1753107.
Vancouver
1.Sinan Kocagöz, Fatih Yücalar, Emin Borandag, Ender Şahinaslan. AutoGluon-Based Performance Analysis for Multi-Class Network Attack Detection. Mus Alparslan University Journal of Science. 2025 Dec. 1;13(2):341-50. doi:10.18586/msufbd.1753107