A hybrid modified grasshopper optimization algorithm and genetic algorithm to detect and prevent DDoS attacks

Abstract

Cyber security has turned into a brutal and vicious environment due to the expansion of cyber-threats and cyberbullying. Distributed Denial of Service (DDoS) is a network menace that compromises victims' resources promptly. Considering the significant role of optimization algorithms in the highly accurate and adaptive detection of network attacks, the present study has proposed Hybrid Modified Grasshopper Optimization algorithm and Genetic Algorithm (HMGOGA) to detect and prevent DDoS attacks. HMGOGA overcomes conventional GOA drawbacks like low convergence speed and getting stuck in local optimum. In this paper, the proposed algorithm is used to detect DDoS attacks through the combined nonlinear regression (NR)-sigmoid model simulation. In order to serve this purpose, initially, the most important features in the network packages are extracted using the Random Forest (RF) method. By removing 55 irrelevant features out of a total of 77, the selected ones play a key role in the proposed model's performance. To affirm the efficiency, the high correlation of the selected features was measured with Decision Tree (DT). Subsequently, the HMGOGA is trained with benchmark cost functions and another proposed cost function that enabling it to detect malicious traffic properly. The usability of the proposed model is evaluated by comparing with two benchmark functions (Sphere and Ackley function). The experimental results have proved that HMGOGA based on NR-sigmoid outperforms other implemented models and conventional GOA methods with 99.90% and 99.34% train and test accuracy, respectively.