Optimization of Intrusion Detection Systems to increase the efficiency using artificial neural networks

摘要

The intrusion detection system is a tool that tries to uncover intrusions and collect evidence of intrusions to repair data and modify system behavior. There are three methods for intrusion detection: detection of abuse, anomaly detection, and detection combined of these two factors with each other. The relationship between different networks and the variety of users has led to major issues such as theft, destruction and manipulation of information. For this purpose, systems known as Intrusion Detection Systems have been developed to identify suspicious behaviors, which today, in computer networks, these systems are used as a defensive tool against attacks and in order to protect information. The main purpose of this paper is to use artificial neural network system to detect intrusions, and also the error percentage of each of the two methods stated in this study is evaluated. Finally, a good solution is suggested to increase the security of the system.