Intrusion Detection using Dense Neural Network in Network System

Abstract

An Network Intrusion Detection System can be perceived as a device, either software or hardware which is utilized to screen the organization for suspicious action or policy violation. In this era of digitization where everyone is using computers for all types of communications- personal, political, financial, etc., it becomes necessary to ensure that the medium of the communication is secure or not. Because nowadays every small scale enterprise, big companies, even personal households are having their own server. The new technologies are based on the concept of networking. So, an intrusion in such networks can cause bid risks like data breach financial risk or malfunctioning of the devices connected in that network. It might be possible for small networks to be checked manually because the total connection in such networks is less, but when it comes to the big networks where a lot of connections are sending and receiving requests, it is near to impossible for someone to check all the connections manually. In this paper dense neural network are used for detecting the network intrusion and NSL-KDD dataset are used to test the model. The proposed model achieved 98.29% accuracy.