DESIGN A NETWORK INTRUSION DETECTION MODEL BY USING AD-HOC ON-DEMAND MULTIPATH DISTANCE VECTOR (AODMV) AND CLUSTER BASED ROUTING PROTOCOL

Abstract

The Intrusion Detection System (IDS) is essential for network security, but its complex environment can result in high false detection rates due to the large number of normal samples. To tackle this issue, a Cluster Based Routing Protocol, integrated to Enhanced Generative Adversarial Network with Bidirectional Long Short-Term Memory and Cross-correlated Convolutional Neural Network (CBRP-EGAN-BiLSTM-CCNN) has been developed in MANET. First Cluster based MANET environment was created by using Ad-hoc On-demand Multipath Distance Vector (AODMV) routing protocol. Various routing attacks are simulated and network parameters are learned from each and every node and transferred to Cluster Heads (CHs). CHs share their local and global information among them using Cluster based Routing Protocol (CBRP).The dataset has been obtained by collecting the network parameters respective to attacks simulation. This dataset is used to train the EGAN-BiLSTM-CCNN model and it has been deployed within each CH for intrusion detection, achieving a balance between security and performance in MANETs and to be more efficient in finding the external attacks. In this paper it has also been proved that using Ad-hoc On-demand Multipath Distance Vector (AODMV) routing protocol will provide more accuracy in various network parameters than Ad-hoc On-demand Distance Vector (AODV) protocol.