Design of an Efficient Hybrid-Attack Classification and Mitigation Model for Heterogeneous Wireless Networks

Wireless networks have become an integral part of modern communication systems. However, they are vulnerable to security threats due to the inherent nature of wireless communication. Existing attack detection & mitigation models either work on a limited set of attacks, or cannot be scaled for larger network scenarios. To overcome such issues, this paper proposes the design of an efficient hybrid-attack classification and mitigation model for heterogeneous wireless networks. The model initially collects contextual communication data samples from different network components and uses a hybrid approach that combines Antlion Optimization (ALO) with Analytical Hierarchical Processing (AHP) rule-based systems to classify and mitigate different types of attacks in wireless networks. The proposed model is designed to work in heterogeneous wireless networks, where different types of devices with different capabilities and specifications are connected to the same set of network scenarios. The model was tested on realtime attacks including Denial of Service (DoS), Man-in-the-Middle (MitM), and Rogue Access Point (RAP) attacks. It was observed that the model was capable of mitigating these attacks with 9.5% higher accuracy, 4.9% higher precision, and 2.5% lower delay when compared with existing models. Thus, the proposed model can assist in enhancing the security of wireless networks and provide better protection against network threats.