Creative Commons source reading · Machine learning for performance
Intelligent DDoS Attack Detection in Software-Defined Networks Using Explainable Machine Learning
Javaid Ahmad Malik; Naila Samar Naz; Muhammad Saleem; Muhammad Adnan Khan
Originally published in Sensors (Basel) · 2026-09-03
From the article
Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.
Abstract
The recent trend of Software-Defined Networking (SDN) has posed significant cybersecurity challenges as a result of its centralized control architecture, dynamic traffic behavior, and high programmability. Although these attributes improve network flexibility and management, they also increase vulnerability to Distributed Denial-of-Service (DDoS) attacks that can overwhelm network resources and disrupt services. Traditional signature- and rule-based detection methods may struggle with evolving traffic patterns and generate excessive false alarms. Machine learning offers a more promising solution that can learn the complex traffic patterns and separate malicious traffic from normal traffic. Most machine learning models, however, are black-box models that provide only superficial insight into the model predictions. Explainable…
5. Results
In SDN, detecting ransomware is difficult, given that malicious traffic may be hard to distinguish from normal traffic, can change quickly, and can exploit encrypted or obfuscated channels. To solve these challenges, the proposed explainable machine learning model was implemented in a Google Colab Python 3.12.13-based environment and tested with various classification methods. The preprocessed dataset was split into 70% training and 30% testing data, with the training data used to train the DDoS attack traffic pattern and the testing data used to evaluate the model’s generalization on unseen data. The accuracy, precision, sensitivity, specificity, F1-score, negative predictive value, false-positive rate, false-negative rate, balanced accuracy, Matthews correlation coefficient, Cohen’s kappa, and ROC-AUC were used to assess the…
6. Conclusions
Reliable DDoS attack detection is increasingly essential in SDN environments because delayed or inaccurate identification can lead to data encryption, service disruption, lateral propagation, and compromise of critical network resources. This challenge is intensified by rapidly evolving ransomware variants, encrypted communication, dynamic traffic behavior, and the growing similarity between malicious and legitimate flows. Traditional signature- and rule-based mechanisms remain effective mainly against known attacks, while many machine learning approaches provide strong predictions without sufficient transparency, limiting analyst trust and practical deployment. To address these limitations, this research developed an explainable machine learning framework that combines multiple classifiers with SHAP- and LIME-based interpretation.…
Editorial reading guide
- What data created and tested the model, and was evaluation independent?
- What is the cost of a false positive, false negative or out-of-distribution decision?
