BoT-IoT: Detection of DDoS Attacks in Internet of Things for Smart Cities

The recent research in technology brought a new era called the Internet of Things (IoT). This modern technology created internet-connected things such as smartphones, smart education and smart cities etc. Smart cities brought various facilities and new challenges in the digital world and it faces many security threats, Distributed Denial of Service (DDoS) attack is one of the most critical attack in the network security field. For this purpose, an effective existing BoT-IoT dataset is used for training and testing the reliability of the system along with various types of attack categories and subcategories. To enhance the security in smart cities, this paper presents an architecture based on the detection of DDoS attack using different machine learning (ML) approaches. The main goal of the paper is to implement different machine learning algorithms such as Random Forest (RF), Naive Bayes (NB) and Decision Tree (DT) to analyse the performance of DDoS attacks using the BoT-IoT dataset. The highest accuracy achieved by the machine learning algorithms Random Forest (RF) and Decision Tree (DT) is 91 % and 91\% respectively using the most familiar BoT-IoT dataset.