Discrete Hopfield Neural Network Model for Secure Electrical Routing in VANETs to Avoid Blackhole Attacks

Intelligent Transportation Systems (ITS) depend heavily on Vehicle Ad Hoc Networks (VANETs) to establish vehicle-to-vehicle communication because these networks improve both safety performance on the roads and the reduction of traffic congestion. Black hole attacks represent one of the major cyber threats that affect the secure operation of Vehicle Ad Hoc Networks. Black hole attacks against VANET networks represent critical threats to security which can generate data packet losses along with network instability even with current security evolution efforts. Security measures based on conventional practices lead to substantial false detection situations while their response times remain slow thus preventing real-time mitigation strategies. This study develops a novel Discrete Hopfield Neural Network with Termite Alate Optimization (DHNN-TAO) model to address the mentioned issues. The Mountaineering Team-Based Optimization (MTBO) is the initial procedure that combines network nodes to establish enhanced network stability and effective transmission between nodes. Discrete Hopfield Neural Network (DHNN) identifies black hole attacks through effective detection of malicious nodes after the clustering process ends. The optimization process of hyperparameters in DHNN uses Termite Alate Optimization (TAO). After identification of malicious activity Light Spectrum Optimizer (LSO) works to find secure communication routes between attack-free network segments. The suggested DHNN-TAO attains 1600 kbps throughput, 0.42s routing delay, 7.4ms execution time, 99.1% accuracy, 0.96 packet delivery ratio, and 0.59 control overhead, surpassing the current techniques.