Lightweight Multi‐Hop Clustering With Cross‐Layer Intelligence for <scp>VANET</scp> Malicious Behavior Detection

ABSTRACT Future vehicular ad hoc networks (VANETs) require fast, secure communication to support road‐safety applications. However, high vehicle congestion, sudden link failures, and malicious behaviors make it difficult to maintain stable communication. To accurately detect and mitigate such attacks and failures, several security and coordination strategies are established. Specifically, clustering groups of vehicles enhances coordination and attack detection. However, existing clustering models often fail to deliver the expected results in behavioral analysis due to sudden cluster breakdowns, high communication overhead, and poor coordination. To address these challenges, we propose a Lightweight Multi‐Hop Clustering framework with Cross‐Layer Intelligence (LMHC‐CI) for real‐time malicious detection in VANETs. The study aims to enhance cluster stability and detection accuracy while maintaining low computational and communication costs. The suggested research also leverages cross‐layer intelligence to enable efficient clustering and detection decisions. The model is simulated using two publicly available datasets: The Vehicular Clustering Dataset and the VANET Malicious Node Dataset. Simulation results indicate that the proposed model achieves 99.6% detection accuracy. The adaptive H‐node remains within 0.15–0.35 and reduces unnecessary role changes after convergence. Also, multi‐hop aggregation reduces EPC packet overhead as hop count increases. This will reduce cluster reformation and routing complexity compared to existing methods.