Multi-Parallel Adaptive Grasshopper Optimization Technique for Detecting Anonymous Attacks in Wireless Networks

For a number of years, due to exponential increase in the demand for sustainable environment, suspicious activities have recently been identified as over-serious threats that are continually processing and growing. Identifying suspicious activities in the domain of cyber security is considered as a growing concern of research. To deal with suspicious threats, network requires traffic surveillance accompanied by beardown security policies. In order to handle data outflow, spoofing, disruption of service, energy exploiting, and insecure gateways range of attacks issues, the existing intrusion detection systems (IDSs) have observed to be less efficient as many of them are not able to detect anomalies with the change in the definition of the attack. To build a protected system against various cyber-attacks in computer networks, in this study, we introduce a multi-parallel adaptive evolutionary technique to utilize adaptation mechanism in the group of swarms for network intrusion detection. After that, simulated annealing is incorporated into multi-parallel adaptive grasshopper optimization technique to further improve the agent quality of individual after each iteration. It has revolutionized in the recent era for efficient threat detection with great performance in a certain time limit. The simulations are performed on three IDS datasets such as NSL-KDD, AWID-ATK-R, and NGIDS-DS. The proposed technique is compared with various existing techniques using different evaluation metrics. The comparative analysis demonstrates that the applicability of proposed technique concerning its merits outperforms the others algorithms.