A two stage hybrid intrusion detection using genetic algorithm in IoT networks

Abstract

Today, almost 90% of the technology in usage is linked with IoT (Internet of Things). which brings the question, what is IoT? Internet of things is a system of co-related computers, electronic devices, and objects. IoT essentially controls almost every online service which we avail without human -to-human interaction. An IDS is a hardware or software system that automatically monitors, identifies, and alerts a computer or network against attacks and intrusions. The proposed hybrid model makes use of genetic algorithm with UNSW NB-15 dataset which contains multiple classes of attack to provide a huge variety of attacks which will help to simulate different kinds of attack which will help train the model better. We have used CNN and LSTM model for extracting features. By detecting the attacks quickly, we can identify potential intruders and limit the damage. Feature selection and classification have been performed using Generic algorithm. This hybrid model helps to check whether the alert is an attack or not, if yes what kind of attack is it. the proposed Hybrid model works better than a conventional intrusion detection system, we got 99.38% accuracy from this model.