NIDS: An Efficient Network Intrusion Detection Model for Security of Big Data Using Different Machine Learning classifiers

Abstract

Security of the big data is one of the important challenges which needs to be addressed by designing an efficient network intrusion model for detecting the unauthenticated intruders in the network. The model should be able to detect the validity of the packet. The detection of intrusions in network was already represented by multiple researchers using different algorithms which still needs instant addressing. Proposing a machine learning classifier algorithm for intrusion detection. The KDD intrusion dataset is used in training the machine for identifying the different intrusions of the network traffic. The machine must be trained efficiently using the different classification algorithms and the security for the data needs to be attained by identifying the invalid network packets. The experimental results demonstrate that the random forest ensemble machine learning classifier is having highest accuracy of 0.2 % when compared with the existing research results in the identification of different intrusions towards the network packets.