Abstract
A Mobile Ad-Hoc Network (MANET) is a convenient wireless infrastructure which presents many advantages in network settings. With Mobile Ad-Hoc Network, there are many challenges. These networks are more susceptible to attacks such as black hole and man-in-the-middle (MITM) than their corresponding wired networks. This is due to the decentralized nature of their overall architecture. In this paper, ANN classification methods in intrusion detection for MANETs were developed and used with NS2 simulation platform for attack detection, identification, blacklisting, and node reconfiguration for control of nodes attacked. The ANN classification algorithm for intrusion detection was evaluated using several metrics. The performance of the ANN as a predictive technique for attack detection, isolation, and reconfiguration was measured on a dataset with network-varied traffic conditions and mobility patterns for multiple attacks. With a final detection rate of 88.235%, this work not only offered a productive and less expensive way to perform MITM attacks on simulation platforms but also identified time as a crucial factor in determining such attacks as well as isolating nodes and reconfiguring the network under attack. This work is intended to be an opening for future malicious software time signature creation, identification, isolation, and reconfiguration to supplement existing Intrusion Detection Systems (IDSs).
Highlights
Computer security is one of the areas in computer technology which have attracted much interest from many security professionals and “lay” persons. is field was necessitated by previously known and newly developing techniques which afford attackers the means to launch sophisticated attacks, giving them access to resources on networks and compromising those networks in the process
MANETs could be seen as VANETs, internet-based mobile ad hoc networks (MANETs), or military-based MANETs. ese broad categorizations imply that MANETs have comprehensive operational capabilities
Even the various attacks could be broken down based on which software application they have been tuned to violate. e man-in-the-middle attack, for instance, has a slight variant called the man-in-the-browser attack which is specific to browser-based applications and services Journal of Computer Networks and Communications
Summary
Computer security is one of the areas in computer technology which have attracted much interest from many security professionals and “lay” persons. is field was necessitated by previously known and newly developing techniques which afford attackers the means to launch sophisticated attacks, giving them access to resources on networks and compromising those networks in the process. Technological development represents possibly the one single area where civilians can compete on a par with the military; it has over the last couple of years offered numerous challenges to both worlds Machine learning algorithms such as support vector machines, neural networks, and others hold promise for learning the complex behavioural patterns needed for cyber defense. Is has led to new frontiers and possibilities in deep learning (a set of machine learning algorithms targeted at modelling high-level abstractions) [10, 11] It is against this backdrop that this research has been carried out to use ANN techniques to solve the problem of the man-in-the-middle attack. Is work presents introduced neural network techniques for detecting fraudulent nodes involved in man-in-the-middle spoofing attacks which constitutes one of the most challenging types to detect and prevent. Based on the information acquired from observed scenarios, the system could adapt the network to counteract or curtail future exploits
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
