Abstract :

The Rapid Growth Of The Internet Of Things (IoT) Has Introduced Significant Security Challenges Due To The Large Number Of Interconnected Devices And Their Limited Computational Capabilities. IoT Networks Are Highly Vulnerable To Various Cyber Threats Such As Distributed Denial Of Service (DDoS), Spoofing, And Unauthorized Access. Traditional Security Mechanisms Are Often Insufficient To Handle The Dynamic And Complex Nature Of IoT Environments. This Project Proposes A Network Intrusion Detection System (NIDS) Based On Machine Learning Techniques To Enhance IoT Security By Identifying Malicious Activities In Real Time. The System Analyzes Network Traffic Data And Extracts Relevant Features Such As Packet Size, Protocol Type, Connection Duration, And Traffic Patterns. Machine Learning Algorithms Such As Decision Tree, Random Forest, And Support Vector Machine (SVM) Are Applied To Classify Network Behavior As Normal Or Malicious. Data Preprocessing Techniques Including Normalization, Feature Selection, And Handling Imbalanced Datasets Are Implemented To Improve Model Performance. The Trained Models Are Capable Of Detecting Various Types Of Attacks With High Accuracy And Reduced False Positives. Experimental Results Show That Machine Learning-based Intrusion Detection Systems Significantly Outperform Traditional Rule-based Approaches In Terms Of Accuracy And Adaptability. Among The Implemented Models, Random Forest Achieves The Highest Detection Accuracy Due To Its Ability To Handle Complex Patterns And Large Datasets. However, Challenges Such As Resource Constraints In IoT Devices And Evolving Attack Patterns Remain. This Project Demonstrates The Effectiveness Of Learning-based Approaches In Securing IoT Networks And Provides A Foundation For Developing Intelligent And Scalable Intrusion Detection Systems.

Published:

08-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

1906-1912

Section:

Articles

License:

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

How to Cite