Machine Learning Enabled Framework for Classification and Detection of Intrusion in MANET

An Intrusion Detection System is a necessity in order to ensure the security of the existing network and user data which is travelling across in the network. Because of the rapid development of network technologies, the identification of dangers based on the analysis of contextual information may be application and network-specific. A remedy to such a challenge may be found in the form of a hybrid intrusion detection system (IDS) which uses machine learning algorithms for optimization. Many possible attacks are viable in a network, but our study id limited to few of them. In one of the popular attack known as denial of service(DOS) attack, the approach is to overwhelm the victim's MANET network with an overwhelming number of packets. It is now possible for this kind of attack to create substantial issues for networks of any scale. When analyzing high-performance hybrid intrusion detection systems, one of the most critical challenges is the processing of vast volumes of information including a large number of features. An excessive quantity of features may slow down the training and testing process, increase resource usage, and decrease detection accuracy. This can be a problem for malicious pattern recognition, which can be inhibited as a result. This article provides a detailed description of a framework for an intrusion detection system that takes use of machine learning. As a result, it is essential to bring the size of the benchmark dataset down to a more manageable level and get rid of any unnecessary features. Cleansing up data sets may be accomplished by the use of preprocessing, which involves deleting out-of-range numbers, uncommon combinations of data, and missing information. In order to improve the accuracy of classifiers, it is common practice to apply methods known as feature selection (FS) in order to rid a dataset of data points that are extraneous or unneeded. In the paper there were three machine learning techniques namely SVM, Naïve Bayes and ID3 which were considered for comparative study. It was observed that SVM is achieving higher accuracy in intrusion data classification and detection.