Convolution Neural Network based Overhead Reduced Intrusion Detection System

Abstract

Attacks in wireless sensor networks (WSNs) aim to prevent or eradicate the network's ability to perform its anticipated functions. Intrusion detection is a defense used in wireless sensor networks that can detect unknown attacks. Due to the incredible development in computer-related applications and massive Internet usage, it is indispensable to provide host and network security. The development of hacking technology tries to compromise computer security through intrusion. Intrusion detection system (IDS) was employed with the help of machine learning (ML) Algorithms to detect intrusions in the network. In recent work   Pattern Matching aware Replicated Neural Network based Intrusion Detection System (PM-RNN-IDS) is introduced for the accurate and faster IDS rate. In this work, Data pre-processing is performed based on Firefly algorithm to eliminate redundant record set and enhanced KNN based imputation is utilized to handle missing value. Feature selection using Modified Particle Swarm Optimization. Finally, Intrusion detection is carried out using Replicator Neural Networks.used. However, dataset which is used in this work has more dimensions and it consumes more storage space. Feature reduction will solve this problem and it is not focused in recent work. Also, Replicator Neural Networks does not produce sufficient accuracy results. To avoid these problems in this work Convolution Neural Network based Overhead Reduced Intrusion Detection System (CNN-OR-IDS) is proposed for the optimal and accurate intrusion detection rate. In this work, modified Firefly algorithm is introduced for redundant data detection and Bagging based KNN Imputation technique is used for the Missing value imputation process. Once the dataset is preprocessed, feature reduction is performed by introducing the method namely Gradually Feature Removal (GFR) method. Once the irrelevant features are removed from the dataset, optimal feature selection is done by using Hybrid of Cuckoo Search with fish swarm algorithm. Finally, intrusion detection process is carried out using Convolutional Neural Network algorithm. Experimental results demonstrate the effectiveness of the proposed work in terms of false positive rate and false alarm rate.