Proficient Red Deer Optimization-based Relevance Vector Machine (PRDO-RVM) for Elevated Intrusion Detection System in MANET

Mobile Ad-hoc Networks (MANETs) are wireless networks composed of autonomous mobile devices that communicate
with each other without relying on a centralized infrastructure. MANET security issues can compromise data confidentiality, integrity, and availability, highlighting the critical need for robust security mechanisms. Intrusion Detection Systems (I.D.S.) are crucial in identifying and mitigating security threats in MANETs. Designing effective I.D.S. for MANETs is inherently challenging due to these networks’ dynamic and resource-constrained nature. To address these challenges, this research proposes the Proficient Red Deer Optimization-based Relevance Vector Machine (PRDO-RVM) for intrusion detection in MANETs. PRDO-RVM leverages the sparsity-inducing properties of Relevance Vector Machine (RVM) and the efficient optimization capabilities of Red Deer Optimization to achieve accurate and efficient intrusion detection in dynamic network
environments. By effectively identifying and classifying intrusions, PRDO-RVM enhances the security posture of MANETs, mitigating the risks posed by malicious actors and ensuring the integrity and availability of network communications. Using the NSK-KDD dataset, PRDO-RVM is evaluated for its effectiveness in detecting intrusions in MANETs. The results demonstrate the superior classification accuracy and efficiency of PRDO-RVM compared to existing I.D.S. solutions, affirming its potential as a reliable and scalable security mechanism for MANETs.