IOT CYBER ATTACK DETECTION

Abstract

The rapid proliferation of Internet of Things (IoT) devices has transformed modern life, enabling smarter homes, cities, and industries. However, this connectivity also exposes IoT systems to a wide range of cyber threats, including malware, ransomware, denial-of-service (DoS) attacks, data breaches, and unauthorized access. Traditional security measures often fall short due to the resource constraints and heterogeneity of IoT devices. This research focuses on developing an efficient cyber attack detection system for IoT networks by leveraging a combination of signature-based detection, anomaly detection, and machine learning techniques. By monitoring network traffic and device behavior in real time, the system can identify potential threats and respond proactively, reducing the risk of data loss and service disruption. Additionally, the integration of edge computing and federated learning enhances the scalability and privacy of the detection framework. Experimental results demonstrate that the proposed system achieves high accuracy in detecting various attack types while maintaining low latency, making it suitable for real-world IoT environments