Abstract :

Distributed Denial Of Service (DDoS) Anomaly Detection In Software Defined Networks (SDNs) Plays A Crucial Role In Safeguarding Network Infrastructure From Malicious Attacks. In This Study, The InSDN Dataset Is Used To Evaluate Various Machine Learning And Deep Learning Algorithms For Detecting DDoS Anomalies. The Techniques Explored Include Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), Bidirectional LSTM (BiLSTM), Convolutional Neural Networks (CNN), CNN+BiLSTM, Support Vector Machines (SVM), Random Forest, AdaBoost, XGBoost, Decision Trees, Logistic Regression, K-Nearest Neighbors (KNN), And A Voting Classifier. Among These Models, The Voting Classifier Demonstrated Superior Performance, Achieving An Accuracy Of 99.9%, Outperforming Other Methods In Terms Of Accuracy, Precision, Recall, And F1-score. The Proposed Approach Highlights The Effectiveness Of Ensemble Learning In Enhancing The Detection Capabilities Of DDoS Anomalies, Thereby Providing A Robust Solution For Network Security In SDNs. The Results Indicate That The Voting Classifier Offers A Promising Direction For Future Research In Anomaly Detection For SDNs. Index Terms - DDoS Detection, Software Defined Networks (SDNs), InSDN Dataset, Machine Learning, Deep Learning, Voting Classifier.

Published:

02-12-2025

Issue:

Vol. 25 No. 12 (2025)

Page Nos:

33-43

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite