ExpSSOA-Deep maxout: Exponential Shuffled shepherd optimization based Deep maxout network for intrusion detection using big data in cloud computing framework. Issue 124 (January 2023)

• Record Type: Journal Article
• Authors: Pandey, Bishwajeet Kumar; M．R．M．, Veeramanickam; Ahmad, Shabeer; Rodriguez, Ciro; Esenarro, Doris
• Is Part Of: Computers & security. Issue 124(2023)
• Publication Date: 2023-01
• Subjects: Intrusion detection -- Deep Maxout network -- Information gain -- Shuffled shepherded optimization -- Exponential weighted moving average; Computer security -- Periodicals; Electronic data processing departments -- Security measures -- Periodicals; 005.805
• DOI: 10.1016/j.cose.2022.102975
• Languages: English
• ISSNs: 0167-4048

Abstract

Abstract: The evolution of the Internet produced a large quantity of information. This makes the internet world more complex and affected by powerful attacks. In modern networks, the Intrusion Detection System (IDS) acts as a significant function for network security. The IDS can be either anomaly or signature-based behavior detection. Recently, several detection approaches have been proposed by researchers to find network intrusions. In this paper, a deep learning approach to intrusion detection using the Exponential Shuffled Shepherded Optimization Algorithm (ExpSSOA) is proposed. The proposed ExpSSOA combines the exponential weighted moving average (EWMA) and the shuffled shepherded optimization algorithm (SSOA). The proposed ExpSSOA-based Deep Maxout network for intrusion detection is examined using the MQTT-IOT-IDS2020 dataset and the Apache Web Server dataset. According to the experimental results using the Apache webserver dataset, the suggested ExpSSOA-Deep maxout network offers a better result with an accuracy of 0.883, an F-measure of 0.8768, a precision of 0.8746, and a recall of 0.8564.