An Intrusion Detection Approach using Hierarchical Deep Learning-based Butterfly Optimization Algorithm in Big Data Platform

Abstract

In recent times, a massive count of data and their increase gradually changed the significance of data security and data analysis methods for Big Data. An intrusion detection system (IDS) is a scheme which analyzes and monitors data for detecting some intrusion from the system or network. Massive volume, variety, and maximum speed of data created in the network develop the data analysis procedure for detecting attacks with typical approaches highly complex. Big Data systems can be utilized in IDS for managing Big Data for accurate and effectual data analysis procedures. This study develops an Intrusion Detection Approach using Hierarchical Deep Learning-based Butterfly Optimization algorithm (ID-HDLBOA) in Big Data Platform. The presented ID-HDLBOA technique combines the concept of DL with hyperparameter tuning process. In the presented ID-HDLBOA technique, hierarchical LSTM model is provided for intrusion detection purposes. Finally, BOA is used as a hyperparameter tuning strategy for the LSTM model and it results in improvised detection efficiency. The experimental validation of the ID-HDLBOA technique is assessed on benchmark intrusion dataset and the model gives the accuracy value of 98%. Wide-ranging experiments were performed and the outcomes emphasized the supremacy of the ID-HDLBOA algorithm.