Analysis of Attack Detection Using Various Techniques over Internet of Things

Abstract

Internet of Things (IoT) has become one of the fastest-growing technologies and has been broadly applied in various fields. IoT, networks contain millions of devices with the capability of interacting with each other and providing functionalities that were never available to us before. These IoT networks are designed to provide friendly and intelligent operations through big data analysis of information generated or collected from an abundance of devices in real time. However, the diversity of IoT devices makes the IoTenvironments more complex and more vulnerable to various attacks compared to traditional computer networks.Hence, the misclassification error rate, accuracy and computational complexity are main issues for the given datasets. To overcome these issues, the existing methods are analyzed various techniques of swarm intelligence algorithms and classification methods which can be applied to bring out hidden knowledge from the specified dataset. There are different methods available for classification of attack detection dataset which is divided into three main categories, attack detection on IoT, swarm intelligence algorithms for attack detection and classification. Each of this technique has their own advantages and disadvantage. The comparative analysis evaluated on the basis of accuracy percentage on the application of various classification techniques like Software-defined network (SDN)-Fuzzy Neural Network (FNN), Random Neural Network (RNN), Hybrid Deep Learning based Convolutional Neural Network -Adaptive Neuro-Fuzzy Inference System (IFFO-HDLCNN + ANFIS) andTunicate Swarm Algorithm (TSA)-Long Short-Term Memory-Recurrent Neural Network (LSTMRNN) model approaches. The experimental result shows that the TSA-LSTMRNN algorithm provides better performance in terms of higher accuracy, precision, recall and f-measure rather than the other existing methods.