IWP-CSO TECHNIQUE FOR FEATURE OPTIMIZATION FRAMEWORK AND A HYBRID HNA-NN TECHNIQUE FOR CLASSIFICATION

Abstract

Supervisory Control and Data Acquisition (SCADA) systems are widely used in many applications includes power transmission and distribution for situational awareness an,d control. Identifying and detecting intrusions in a SCADA is a critical and demanding task in recent days. For this purpose, various Intrusion Detection Systems (IDSs) are developed in the existing works. But, it has some drawbacks include, it has high false positive and false negative rates, it cant detect the encrypted date and it supports only for detecting the external intrusions. In order to overcome all these issues, an Intrusion Weighted Particle based Cuckoo Search Optimization (IWPCSO) and Hierarchical Neuron Architecture based Neural Network (HNA-NN) techniques are proposed in this paper. The main intention of this paper is to detect and classify the intrusions in a SCADA network based on the optimization. At first, the input network dataset is given as the input, where the attributes are arranged and the clusters are initialized. Then, the features are optimized to select the best attributes by using the proposed IWP-CSO algorithm. Finally, the intrusions in a network are classified by employing the proposed HNA-AA algorithm. The experimental results evaluate the performance of the proposed system in terms of sensitivity, specificity, precision, recall, accuracy, Jaccard, Dice and false detection rate.

Shitharth Selvarajan

Lecturer in Cyber Security

My research interests include Cyber Security, Blockchain, Critical Infrastructure & Systems, Network Security & Ethical Hacking.