ech T Press Science Computers, Materials & Continua DOI:10.32604/cmc.2022.020938 Article DNNBoT: Deep Neural Network-Based Botnet Detection and Classifcation Mohd Anul Haq and Mohd Abdul Rahim Khan * Department of Computer Science, College of Computer and Information Sciences, Majmaah University, Al-Majmaah 11952, Saudi Arabia * Corresponding Author: Mohd Abdul Rahim Khan. Email: m.khan@mu.edu.sa Received: 15 June 2021; Accepted: 30 August 2021 Abstract: The evolution and expansion of IoT devices reduced human efforts, increased resource utilization, and saved time; however, IoT devices create signifcant challenges such as lack of security and privacy, making them more vulnerable to IoT-based botnet attacks. There is a need to develop effcient and faster models which can work in real-time with effciency and stabil- ity. The present investigation developed two novels, Deep Neural Network (DNN) models, DNNBoT1 and DNNBoT2, to detect and classify well-known IoT botnet attacks such as Mirai and BASHLITE from nine compromised industrial-grade IoT devices. The utilization of PCA was made to feature extraction and improve effectual and accurate Botnet classifcation in IoT environments. The models were designed based on rigorous hyperparameters tuning with GridsearchCV. Early stopping was utilized to avoid the effects of overftting and underftting for both DNN models. The in-depth assessment and evaluation of the developed models demonstrated that accuracy and effciency are some of the best-performed models. The novelty of the present investigation, with developed models, bridge the gaps by using a real dataset with high accuracy and a signifcantly lower false alarm rate. The results were evaluated based on earlier studies and deemed effcient at detecting botnet attacks using the real dataset. Keywords: Botnet; network monitoring; machine learning; deep neural network; IoT threat 1 Introduction The expansion of the Internet of Things (IoT) network and its applications have risen enormously due to upgrading communication ef fciency, low cost, and ever-increasing demand. The IoT devices have been developed and utilized for numerous sectors, including smart cities, smart grid, smart manufacturing and maintenance, intelligent transport, security and surveillance, precision agriculture, utilities such as power, electricity and water, supply chain, and inventory optimization, more. Over the past few years, the number of sensor-based smart devices that can communicate over the internet without human involvement is growing exponentially. It will be reaching around 30 billion by 2050 [1]. However, the massively increasing numbers and global presence of IoT have become an opportunity for hackers to exploit the security and privacy of This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.