MACHINE LEARNING BASED WIRELESS NETWORK SECURITY HUB

Abstract

The advancement of wireless network technology brings new challenges in terms of security, especially against increasingly complex attacks. This research proposes the development of a Machine Learning-based Wireless Network Security Hub that functions as a centralized platform for real-time threat management and detection. The system integrates classification and anomaly detection algorithms to identify attack patterns such as Denial of Service (DoS), Man-in-the-Middle, and Eavesdropping. The methods employed include network traffic data collection, model training using supervised and unsupervised learning, and system performance evaluation using accuracy metrics and response time. Test results demonstrate that the system can improve threat detection rates up to 95% while maintaining optimal response times for medium-scale network requirements. These findings highlight the significant potential of Machine Learning in strengthening wireless network security through automated and adaptive solutions..