Modelling of Optimal Quantum Neural Network for DDoS Attack Classification in Wireless Sensor Networks

Wireless Sensor networks (WSN) are a new technology and are huge potential that is utilized in crucial moments such as battlefields and commercial applications namely habitat monitoring and smart homes, building, traffic surveillance, etc. Among the main problems WSNs currently affecting is security. But the utilization of sensor nodes (SNs) from the unattended platform creates the networks vulnerable to variation of potential attacks, the inherent power and memory restrictions of SNs create ordinary security solutions impossible. This article develops a Spotted Hyena Optimizer with Quantum Neural Network for DDoS Attack Classification (SHOQNN-AC) technique for WSN. The major intention of the SHOQNN-AC technique lies in the proper identification of DDoS attacks in the WSN. To accomplish this, the SHOQNN-AC technique performs data scaling process using min-max scaler. For DDoS attack detection, the SHOQNN-AC technique employs QNN classification model which proficiently recognizes the DDoS attacks in the network. To boost the attack detection efficiency of the SHOQNN-AC technique, the SHO algorithm is exploited for parameter selection procedure. The performance validation of SHOQNN-AC technique is tested on benchmark WSN-DS dataset. The experimental outcome demonstrates the significance of the SHOQNN-AC algorithm over other models.