MRPO-Deep maxout: Manta ray political optimization based Deep maxout network for big data intrusion detection using spark architecture. (December 2022)

• Record Type: Journal Article
• Authors: Kurni, Muralidhar; S． Md, Mujeeb; Yannam, Bharath Bhushan; T, Arun Singh
• Is Part Of: Advances in engineering software. Volume 174(2022)
• Publication Date: 2022-12
• Subjects: Intrusion detection system -- Big data -- Apache spark -- Data augmentation -- Deep maxout network; Computer-aided engineering -- Periodicals; Engineering -- Computer programs -- Periodicals; Engineering -- Software -- Periodicals; Periodicals; 620.0028553
• DOI: 10.1016/j.advengsoft.2022.103324
• Languages: English
• ISSNs: 0965-9978

Abstract

Highlights: The large quantity of data is termed as big data with different characteristics. Intrusion detection system (IDS) is the system used to examine as well as analyze data for detecting intrusions in network or system. Accordingly, high quantity as well as higher speed of information in network enables data analysis procedure to find intrusions using conventional intrusion detection methods. The increasing demand of big data increases attacks in network, detecting intrusion in big data environment still results a challenging task. To solve the issues faced by existing methods and to detect the intrusions more accurately, an efficient intrusion detection method is designed by proposed Manta Ray Political Optimization (MRPO)-based Deep maxout network. Abstract: An intrusion detection system (IDS) is used to examine as well as analyze data for detecting intrusions in a network or system. This paper proposes an efficient intrusion detection method, named Manta Ray Political Optimization (MRPO)-based Deep maxout network. Here, the training procedure of the Deep maxout network is achieved by the proposed MRPO algorithm that is derived by integrating Manta Ray Foraging Optimization (MRFO) and Political Optimizer (PO). Initially, different subsets of data are formed by partitioning the input data and each data subset is processed by slave nodes to pre-process the data. The wrapper-based model and fisher score are used to select features such that the fusion of these features is based on Hellinger distance. With selected features, the dimensionality of data is increased using the data augmentation and based on data augmented output, and Deep maxout network is applied to detect normal and abnormal behavior. The proposed method attains maximum testing accuracy, True Positive Rate (TPR), and True Negative Rate (TNR) of 0.939, 0.943, and 0.910 by the Apache webserver dataset. When the training data is 90, the accuracy of the proposed method is 9.15%, 6.38%, 5.75%, 2.66%, 2.12%, 1.49%, 074%, 1.70%, and 4.79% higher when compared to the existing approaches namely, Hybrid deep learning, RCCRO-FCM, HHO-based DBN, CGO+ensemble SVM, Deep maxout network, PO-based Deep maxout network, MRFO- based Deep maxout network, STL-HDL, and ExpSLO enabled DRN.