Abstract :

The Rapid Proliferation Of Internet Of Things (IoT) Devices In Smart Home Environments Has Significantly Improved Convenience, Automation, And Energy Efficiency, But It Has Also Introduced Serious Security And Privacy Challenges. Smart Homes Consist Of Interconnected Sensors, Cameras, Smart Appliances, And Controllers That Continuously Exchange Data Over Home Networks And Cloud Platforms. Due To Their Limited Computational Resources, Heterogeneous Architectures, And Often Weak Security Configurations, IoT Devices Are Highly Vulnerable To Cyber Threats Such As Malware Infections, Unauthorized Access, Denial-of-service Attacks, And Data Exfiltration. Traditional Security Mechanisms Designed For Conventional Networks Are Insufficient To Address The Dynamic And Complex Traffic Patterns Of IoT Environments. In This Context, Network Anomaly Detection Has Emerged As A Promising Approach For Identifying Abnormal Behavior That Deviates From Normal Operational Patterns. This Project Focuses On IoT Network Anomaly Detection In Smart Homes Using Machine Learning Techniques To Automatically Learn Normal Traffic Behavior And Identify Suspicious Activities. By Analyzing Network Traffic Features Such As Packet Flow, Protocol Usage, Timing Patterns, And Communication Frequency, Machine Learning Models Can Detect Unknown And Zero-day Attacks That Signature-based Systems Often Fail To Recognize. The Proposed Approach Leverages A Random Algorithm–based Learning Strategy To Improve Detection Accuracy While Maintaining Low Computational Overhead, Making It Suitable For Real-time Deployment In Smart Home Gateways. The System Aims To Enhance Smart Home Security By Providing Early Detection Of Anomalies, Reducing False Alarms, And Ensuring Data Privacy And Network Reliability. This Study Demonstrates How Intelligent, Data-driven Anomaly Detection Can Play A Crucial Role In Securing Future Smart Home Ecosystems.

Published:

17-6-2026

Issue:

Vol. 26 No. 6 (2026)

Page Nos:

1222-1226

Section:

Articles

License:

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

How to Cite