International Journal of Advances in Applied Sciences (IJAAS) Vol. 9, No. 1, March 2020, pp. 27~33 ISSN: 2252-8814, DOI: 10.11591/ijaas.v9.i1.pp27-33  27 Journal homepage: http://ijaas.iaescore.com An efficient quantum multiverse optimization algorithm for solving optimization problems Samira Sarvari, Nor Fazlida Mohd. Sani, Zurina Mohd Hanapi, Mohd Taufik Abdullah Department of Computer Science, Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Malaysia Article Info ABSTRACT Article history: Received Jun 29, 2019 Revised Nov 2, 2019 Accepted Dec 1, 2019 Due to the recent trend of technologies to use the network-based systems, detecting them from threats become a crucial issue. Detecting unknown or modified attacks is one of the recent challenges in the field of intrusion detection system (IDS). In this research, a new algorithm called quantum multiverse optimization (QMVO) is investigated and combined with an artificial neural network (ANN) to develop advanced detection approaches for an IDS. QMVO algorithm depends on adopting a quantum representation of the quantum interference and operators in the multiverse optimization to obtain the optimal solution. The QMVO algorithm determining the neural network weights based on the kernel function, which can improve the accuracy and then optimize the training part of the artificial neural network. It is demonstrated 99.98% accuracy with experimental results that the proposed QMVO is significantly improved optimization compared with multiverse optimizer (MVO) algorithms. Keywords: Intrusion Detection System Multiverse Optimization Quantum Computing Quantum Multiverse Optimization This is an open access article under the CC BY-SA license. Corresponding Author: Samira Sarvari, Department of Computer Science, Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Serdang, 43400 Seri Kembangan, Selangor, Malaysia. Email: samirasarvari82@yahoo.com 1. INTRODUCTION The increase in the number of local networks has led to the continuous development of Internet data and the availability of massive amounts of network data has promoted the development of information technology, which requires careful attention. As a result, this evolution, in turn, has increased the system's vulnerability to various threats [1]. Any intrusion can have catastrophic consequences. For example, personal data may be destroyed, corrupted or illegally accessed as a result of breaches of confidentiality. In addition, infringements of integrity can lead to alteration of personal data. Computer network security has become a promising tool for secure channels. One of the promising tools for detecting attacks is the intrusion detection system (IDS). Cybersecurity infrastructures use IDS as an essential component and protect systems and infrastructures against various threats. An intrusion detection system consists of data collection, data clearing and pre-processing, intrusion detection, reporting and reasonable action, which is an essential part of these attack detection processes [2]. High classification accuracy and a low false alarm rate are the two main characteristics of well-developed IDS, so it is extremely important to develop mechanisms for intrusion detection in view of the conviction that suspicious activities can be detected by taking measures to prevent further breeding of computer networks or systems [3]. Data classification has been studied extensively in many computer fields and up to now, the development of classification has achieved great achievements and many types of classified technology