Lightbioptimum: An Intrusion Detection System Based on Bio-Inspired Algorithm for VANET

Abstract

In recent years, the development of machine learning-based Intrusion Detection Systems (IDS) has gained significant traction for enhancing data security and identifying threats across diverse network environments. This paper presents a novel lightweight Network Intrusion Detection System (NIDS), named LightBioptimum, specifically designed for Vehicular Ad Hoc Networks (VANETs)—a domain marked by high mobility, dynamic topology, and real-time constraints. The proposed system integrates a bio-inspired optimization technique, Ant Colony Optimization, with a Tree-based Convolutional Neural Network (Tree-CNN) to enable efficient feature selection and accurate threat classification. Experimental evaluations demonstrate that LightBioptimum achieves outstanding results, surpassing existing models in both accuracy and computational efficiency. Notably, it achieves an F1-score of 97.0% in detecting Distributed Denial of Service (DDoS) attacks, outperforming the Deep Belief Network (DBN), which reached 93.0%. Furthermore, LightBioptimum reduces the detection time for brute force attacks by 32.59% compared to DBN. These results confirm the effectiveness of the proposed system in meeting the stringent performance requirements of VANET environments. As Mobile Edge Computing (MEC) applications continue to proliferate in urban areas, LightBioptimum stands out as a promising real-time security solution for VANET and MEC infrastructures.