Machine Learning Algorithms in Intrusion Detection and Classification

Abstract

The complexities that information systems face are quickly growing. Threats and attacks are framed and executed using new methods that exploit the information contained in networks. When going across subtle domains, knowledge is constantly changing due to the different categories of users, server managers, and those that need to access it. Information device protection is critical against threats such as denial of service attacks and intrusions. Intrusion is a big threat to unauthorized data or lawful network leveraging valid users' identities or any of the network's back doors and vulnerabilities. Intrusion Detection Systems are mechanisms designed to detect intrusions at different stages (IDS). The aim of this research is to improve the efficiency of intrusion detection systems (IDS) by using rule-based techniques and learning-based algorithms for intrusion detection and classification. Neural Networks (NN) , Random Forest and SVM algorithms.The output of rule-based techniques and machine learning algorithms is evaluated using regular datasets such as kddcup 99.