Principal Component Analysis-Multilinear Perceptron-based model for Distributed Denial of Service Attack Mitigation

Abstract

The increasing occurrence of Distributed Denial of Service (DDoS) attacks has caused significant disruptions in global network services, overwhelming targets by flooding them with requests from various sources. This ease of execution and gaining entry to distributed systems for rent has led to increasing financial losses. This paper addresses the growing challenge of IoT devices-targeted Distributed Denial of Service (DDoS) attacks within 4G networks. In this study, a PCA-MLP (Principal Component Analysis-Multi-Layer Perceptron) intrusion detection model combined with a packet-filtering firewall for enhanced prevention is presented. The firewall, utilizing IPtables, selectively permits traffic from trusted sources, successfully blocking nearly 70% of DDoS threats. The PCA-MLP model proposed in this study demonstrated high performance, accurately identifying different types of DDoS attacks with an overall accuracy of 95.35%.