DETECTION OF REAL TIME MALICIOUS INTRUSIONS&ATTACKS IN IOT EMPOWERED CYBERSECURITY

Abstract

The rapid expansion of Internet of Things (IoT) devices has significantly increased connectivity and automation in smart environments. However, this growth has also escalated cybersecurity risks, making IoT networks vulnerable to malicious intrusions, malware attacks, and unauthorized access. Detecting these threats in realtime is crucial to safeguard sensitive data and maintain system reliability. This study proposes a real-time intrusion detection system (IDS) leveraging machine learning and deep learning algorithms to identify anomalous behavior in IoT networks efficiently. The system captures network traffic, analyzes patterns, and predicts potential threats with high accuracy. Experimental results show that the proposed framework improves detection rates while reducing false alarms compared to traditional methods.