Cyber Security System Based on Machine Learning Using Logistic Decision Support Vector

Abstract

Nowadays, we are moving towards cybersecurity against digital attacks to protect systems, networks, and data in developing areas. A collection of technologies and processes is at the core of cybersecurity. A network security system is a feature of network and computer (host) security. Cybercrime leads to billion-dollar losses. Given these crimes, the security of computer systems has become essential to reduce and avoid the impact of cybercrime. We propose the Logistics Decision Support Vector (LDSV) algorithm dealing with this problem. Initially, we collected the KDD Cup 99 dataset to create a network intrusion detection, such as penetrations or attacks, a prognosis model that varies between the "Non Malicious" and "Malicious" standard links. These method finds the cyber-attack category based on the behavior features. In the second step, data preprocessing should be cleaned from errors, and raw data should be converted into a prepared dataset. The third step is Feature Selection (FS) techniques often improve the feature selection process in an Intrusion Detection System (IDS) that is more convenient for using the mean of the Chi-square test (MAC) method. Finally, a classification is done to classify and detect the network intrusion detection based on LDSV for Cyber security. The proposed LDSV simulation is based on the Precision F-Measure, Recall, and Accuracy for the best result.