aspg-2-836-1791417082 20261007235122 American Scientific Publishing Group admin@americaspg.com American Scientific Publishing Group Journal of Cybersecurity and Information Management JCIM 2769-7851 2690-6775 2019 0 1 Andino Maseleno Institute of Informatics and Computing Energy, University Tenaga Nasional, Malaysia Cybersecurity is the process of protecting critical systems and confidential data from digital attacks. With the advent of machine learning, cybersecurity systems can examine the patterns and learns them from preventing similar attacks and responds to fluctuating behavior. Cybersecurity intrusion detection system helps to detect the existence of intrusions in the network and achieves security in confidential data storage and transmission. In this view, this study designs an efficient cockroach optimization (CSO) with kernel extreme learning machine (KELM) model for cybersecurity intrusion detection. The proposed CSO-KELM model can accomplish cybersecurity by the detection and classification of intrusions. The proposed CSO-KELM technique encompasses a three-level process, namely preprocessing, classification, and parameter tuning. The design of the CSO algorithm for the appropriate selection of KELM parameters results in improved classification performance. For examining the betterment of the CSO-KELM technique, a series of experiments were performed on benchmark datasets. The experimental results pointed out the superiority of the CSO-KELM technique concerning several measures. 2019 32 43 836 https://creativecommons.org/licenses/by/4.0/ 10.54216/JCIM.000103 https://www.americaspg.com/journal/2/article/836 https://www.americaspg.com/storage/6770.pdf