Adaptive Ship Rescue Optimization Enabled Deep Learning for Sybil Attack Detection with Secure Transmission in Urban VANET

Future Road transportation is primarily reliant on connected vehicles. Moreover, the Intelligent Transportation Systems support road users through the utilization of Vehicular Ad hoc Networks (VANETs). The rogue node, termed a sybil node, transmits bogus signals to interrupt the system, impacting its security. However, the detection of a Sybil attack is complicated due to the dynamic nature of nodes and stability issues. Adaptive Ship Rescue Optimization-based Deep Kronecker Network (ASRO_DKN)-based Sybil attack detection is proposed to solve such an issue. The VANET simulation is initially carried out, and the Fractional Glowworm Swarm Optimization for Traffic Aware Routing (FGWSO-TAR) is performed. The Sybil attack is detected at the Base Station (BS), where the input data packet is applied to feature extraction, and the attack is detected by the Deep Kronecker Network (DKN). The hyperparameters of the DKN are tuned using the ASRO. The Precision, recall, and F-measure metrics are utilized to validate the ASRO_DKN-based Sybil attack detection in VANET, and the optimum values of 90.84%, 90.48%, and 90.13% are achieved.