Machine Learning for Intrusion Detection in Ad-hoc Networks: Wormhole and Blackhole Attacks Case

Abstract

This paper addresses the security concerns associated with Mobile Ad-hoc Networks (MANET) and proposes a new method for detecting and preventing attacks using machine learning. The study involved the creation of a MANET with 26 nodes in NetSim (Network Simulator) software, followed by the implementation of wormhole and blackhole attacks. A dataset was generated from the network traffic obtained during the simulations, and a machine-learning model was designed to predict and detect these attacks. The model achieved high sensitivity, accuracy and f1 scores of 99%. The effectiveness of the model was tested by developing a real-time application. This method can be applied to any wireless network and is particularly relevant for companies that use Ad-hoc networks for communication.