An efficient feature selection and optimal hybrid classification for intrusion detection system

Abstract

newline Cloud computing offers on-demand services, from which consumers can avail networked storage and computer resources. Due to the fact that cloud is accessed through internet, its data are prone to internal and external intrusions. Cloud Intrusion Detection System will now be able to classify each pattern of testing dataset as either normal or intrusive and in case of intrusion; it will identify the type of intrusion. By comparing each of the actual results with the expected results of testing dataset, the inside-activities of a network have been strongly observed. Hence, it is suitable for detecting intrusions in cloud environment. Network flaws are used by hackers to get access to private systems and data. This data and system access may be extremely destructive with losses. Therefore, this network intrusions detection is utmost significance. While investigating every feature set in the network, deep learning-based algorithms require certain inputs. That s why, an Adaptive Artificial Neural Network Optimized with Oppositional Crow Search Algorithm is proposed for network intrusions detection. It is utilized to detect behaviours that compromise security and privacy within a network or in the context of a computer system. To enhance the identification, cluster-based hybrid classifiers are also proposed in this work. The main goal of the research work is to develop a framework that efficiently manages the feature selection with high accuracy and hybrid classification with the optimal care data and provides security to the data