A novel network intrusion detection method based on metaheuristic optimisation algorithms

Abstract The growing use of the Internet with its vulnerabilities has necessitated adoption Intrusion Detection Systems (IDS) to assure security. IDSs are protective systems that detect outsider infiltrations, unauthorised accesses and malfunctions occurring in computer networks. Intrusions can be detected reported network administrator by using various pieces information such as port scanning irregular traffic detection. detection is a classification problem, identifying effective features an essential aspect methods. Standard methods used for neural networks, fuzzy logic, data mining techniques metaheuristics. One novel metaheuristic algorithms introduced address optimisation problems Horse herd Optimisation Algorithm (HOA). This paper introduces new approach on basis HOA intrusion method uses horse behaviours select intrusions interactions between features. For purpose approach, first updated into discrete algorithm floor function. binarised then converted quantum-inspired optimiser integrating concepts quantum computing improve social horses herd. In computing, Q-bit Q-gate aid striking greater balance exploration exploitation processes. resulting multi-objective algorithm, where objectives chosen from set optimal solutions. MQBHOA, which problem. classification, K-Nearest Neighbour (KNN) classifier applied. To evaluate algorithm’s performance, two sets, NSL-KDD (Network Security Laboratory—Knowledge Discovery Data Mining) CSE-CIC-IDS2018, employed packets classified five categories: normal plus four packet types Denial Service (DoS), User Root (U2R), Remote Local (R2L) Probing (Prob). performance was evaluated compared other well-known algorithms, influence parameters degree investigated. results show 6% more success rate average size feature selection accuracy comparison algorithms. It also demonstrates 99.8% detecting