An Efficient Network Intrusion Detection System for Distributed Networks using Machine Learning Technique

The task to ensure security in a network that is distributed over several nodes is a significant and challenging one. Since the primary objective of a DDoS attack is to prevent authorized nodes from gaining access to the service, this type of attack presents a significant threat to distributed networks. It is highly important that a modular and dependable NIDS must be created for handling DOS attacks in the distributed environment effectively, and in turn, all the nodes are available in the distributed network.The high need for modular techniques required in the detection phase for collecting, storing and analyzing the big data from the nodes in the distributed network poses significant hurdles in finding out the Distributed DOS attack.This research proposes a Big Data-based Distributed Denial of Service Network Intrusion Detection System to address these issues. Important features of the proposed intrusion detection system include a module for detecting network traffic and another for collecting data on that traffic. In this study, micro-batch data processing is employed for traffic feature gathering in the Network collection module and Random Forest (RF) algorithm-based classification technique is used in the traffic detection module for feature selection. For Storing a large number of wary attacks, Hadoop File System (HDFS) is used, and for accelerating the speed of data processing, S park is used as a suggested solution.The method was assessed using the NSL-KDD benchmark dataset to find the accuracy and many other parameters. Experimental results for Accuracy, Recall, F1-Measure and Precision, from the proposed work are compared to those from the machine learning techniques, DT(Decision Tree), PCA RF(Principal Component Analysis Random Forest), NB(Naive Bayes), SVM(Support Vector Machine), and LR (Logistic Regression). According to the experimental findings, the suggested detection algorithm achieved an Accuracy of 99.89%, respectively.