Intelligent Intrusion Detection System using Enhanced Arithmetic Optimization Algorithm with Deep Learning Model

Abstract

The widespread use of interoperability and interconnectivity of computing systems is becoming indispensable for enhancing our day-to-day actions. The susceptibilities deem cyber-security systems necessary for assuming communication interchanges. Secure transmission needs security measures for combating the threats and required developments to security measures that counter evolving security risks. Though firewalls were devised to secure networks, in real-time they cannot detect intrusions. Hence, destructive cyber-attacks put forward severe security complexities, requiring reliable and adaptable intrusion detection systems (IDS) that could monitor unauthorized access, policy violations, and malicious activity practically. Conventional machine learning (ML) techniques were revealed for identifying data patterns and detecting cyber-attacks IDSs successfully. Currently, deep learning (DL) methods are useful for designing accurate and effective IDS methods. In this aspect, this study develops an intelligent IDS using enhanced arithmetic optimization algorithm with deep learning (IIDS-EAOADL) method. The presented IIDS-EAOADL model performs data standardization process to normalize the input data. Besides, equilibrium optimizer based feature selection (EOFS) approach is developed to elect an optimal subset of features. For intrusion detection, deep wavelet autoencoder (DWAE) classifier is applied. Since the proper tuning of parameters of the DWNN is highly important, EAOA algorithm is used to tune them. For assuring the simulation results of the IIDS-EAOADL technique, a widespread simulation analysis takes place using a benchmark dataset. The experimentation outcomes demonstrate the improvements of the IIDS-EAOADL model over other existing techniques

Keywords

• arithmetic optimization algorithm
• deep learning
• feature selection
• intrusion detection
• security