DDoS attack detection in cloud using ensemble model tuned with optimal hyperparameter

Abstract

SummaryDDoS attacks are a type of cloud incursion that lessen service degradation. DDoS attacks target the cloud network with invalid requests, rejecting legitimate requests. Such attacks disrupt the entire cloud architecture, thus it needs efficient detection methods to spot their presence. This study proposes a novel ensemble classification model for DDoS incursion detection. Pre‐processing, feature extraction, and attack detection are the three main components of the suggested intrusion detection system. Improved data imbalance processing is processed during pre‐processing. Features including HOS‐based features enhanced entropy‐based features, correlation features, and raw features are extracted from the pre‐processed data. The generated features are trained using an ensemble model, which integrates classifiers like SVM, RF, NN, LSTM, and DRN, during the attack detection phase. A new hybrid approach known as TUDMA optimally trains the model by setting the ideal weight because DRN provides the final detected outcome. By reducing errors, this ideal training will guarantee an improvement in detection results. The suggested hybrid optimization combines the two techniques, TDO and DMO. The accuracy of the methods FS‐WOA‐DNN, RBF‐PSO, SMA, BRO, SLO, and NMRA was 86.73%, 85.69%, 84.58%, 87.43%, 88.91%, and 89.78%, respectively, while the accuracy of the TUDMA was 95.34% in the 80th learning percentage. Finally, for many measurements, the suggested efficiency is superior to the traditional methods.