Intrusion Detection System using Hybrid Machine Learning for MANET

Abstract

A mobile ad-hoc network (MANET) is an infrastructure-less wireless network and self-organized. During communication MANETs don’t use any proper infrastructure so MANET is prone to various sorts of attacks like distributed denial-of-service(DDoS), Bot,Secure Socket Shell(SSH-Bruteforce), and FTP-BruteForce.To provide adequate se curity against multi-level attacks detection-based schemes should be incorporated ad ditionally to traditionally used prevention techniques because prevention-based tech niques cannot prevent the attacks from compromised internal nodes. In this paper, a hybrid machine learning model with a new feature selection method is proposed for better performance of the Intrusion Detection System. In this proposed model, the In trusion Detection System is built with a combination of supervised and unsupervised machine learning models.The obtained results show that the proposed intrusion detec tion is effective in detecting the DDoS, Bot, SSH-Bruteforce, and FTP-BruteForce type attacks with a high detection rate. The results show KNN (99.99% accuracy), K Means Clustering(99.99% accuracy), Decision Tree (99.99% accuracy and the hybrid also 99.99% accuracy . Finally, the paper concludes with a variety of future research direc tions within the design and implementation of intrusion detection systems for MANETs