The growing popularity of the internet and network services has resulted in an increase in data in all fields. The data are increasing on the daily basis with high speed. This also creates some daunting issues such as security, storage, and so on. Meanwhile, the detection of intrusion from the big data in the ultra-high-speed environment is a critical task. Several intrusion detection methods are carried out to classify the big data based on intrusion and without intrusion. The optimum accuracy of big data classification, however, has yet to be achieved. Hence we proposed a novel ensemble SVM Model, in which the ensemble SVM is incorporated with the Chaos Game Optimization (CGO) algorithm, which can be exploited to enhance the classification accuracy. Our method also classifies the intrusion based on their types. It also classifies almost nine attacks as, Exploits, DoS, Backdoor, Generic, Worms, Analysis, Fuzzers, Shellcode, Reconnaissance. The experimental analysis is carried on the UNSW-NB15 big data dataset. The performance metrics precision, accuracy, recall, F-score are analyzed and compared with the state-of-art works such as BAMS-OIF, SAD, SMLsmBDA, and BDPM. The outcomes depict that the proposed work outperforms all the other existing works in terms of classification accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.