DDoS Attack Detection Using Hybrid Caviar Kookaburra Optimization Enabled SpinalNet in Cloud Computing

Distributed denial-of-service (DDoS) attack is examined as a system anomaly, which is inflicted on network traffic.In the realm of cybersecurity, Distributed Denial-of-Service (DDoS) attacks pose a significant threat, particularly in the context of cloud environments.This form of cyber-attack, characterized by overwhelming network traffic, has become a weapon of choice for cyber terrorists, extortionists, and hackers.Despite the development of numerous conventional mitigation strategies, DDoS attacks continue to escalate in severity, frequency, and volume, posing a persistent challenge to security measures.To address the evolving landscape of DDoS threats, a novel and effective model, Kookaburra Optimization Algorithm CAViaR enabled SpinalNet (KOACAViaR_SpinalNet), is proposed for DDoS attack detection in the context of cloud environments.Initially, input data specified in the given dataset is subjected to data normalization and it is conducted using Z-score normalization.The normalized data is then delivered to the feature selection process and is done using the Soergel metric.In addition to that, the data augmentation process is conducted using bootstrapping.Finally, DDoS attack detection is performed by utilizing SpinalNet, trained by KOACAViaR, which is the assimilation of the Kookaburra Optimization Algorithm (KOA) with the Conditional Autoregressive Value-at-Risk (CAViaR) concept.The experimental results show that KOACAViaR_SpinalNet attained a maximum Accuracy of 91.8%, Precision of 92%, and Recall of 91.5%.