Abstract :

The Rapid Growth Of Internet Of Things (IoT) Networks Has Increased The Exposure Of Connected Devices To Distributed Denial-of-service (DDoS) Attacks, Leading To Service Disruption, Unauthorized Access, And Network Instability. This Paper Presents An Intelligent DDoS Attack Detection And Mitigation Framework That Combines Machine Learning And Deep Learning Techniques To Identify Malicious Network Traffic With High Reliability. The Proposed Approach Employs The IoT-23 Benchmark Dataset For Model Development, Where Data Preprocessing Includes Feature Encoding, Missing Value Handling, Normalization, And Train–test Partitioning To Improve Model Effectiveness. XGBoost And Convolutional Neural Network (CNN) Models Are Trained And Evaluated Using Accuracy, Precision, Recall, F1-score, And Confusion Matrix Analysis To Assess Classification Performance Across Multiple Attack Categories. A Web-based Flask Application Is Integrated With The Trained Models To Enable Real-time Analysis Of Incoming IoT Traffic. Once Malicious Activity Is Detected, The Corresponding Source IP Address Is Automatically Marked For Blocking, Providing An Additional Mitigation Mechanism To Reduce Repeated Attacks. Experimental Evaluation Demonstrates That The CNN Model Achieves Superior Detection Performance With Approximately 98% Accuracy, While XGBoost Attains Around 95% Accuracy, Indicating The Effectiveness Of The Proposed Hybrid Intelligent Framework For Securing IoT Environments. The Developed System Offers A Scalable And Practical Solution For Automated Attack Detection And Timely Mitigation In Modern IoT Networks.

Published:

30-7-2026

Issue:

Vol. 26 No. 7 (2026)

Page Nos:

1317-1322

Section:

Articles

License:

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

How to Cite