A Hybrid Deep Learning Approach for Bottleneck Detection in IoT

Abstract

Cloud computing is perhaps the most enticing innovation in the present figuring situation. It gives an expense-effective arrangement by diminishing the enormous forthright expense for purchasing equipment foundations and processing power. Fog computing is an additional help to cloud infrastructure by utilizing a portion of the less register concentrated undertaking at the edge devices, reducing the end client’s reaction time, such as the Internet of Things (IoT). However, most IoT devices are resource-constrained, and there are many devices that cyber-attacks could target. Cyber-attacks such as Denial of Service (DoS), Distributed Denial of Service (DDoS), and botnets are still significant threats in the IoT environment. Botnets are currently the most significant threat on the internet. A botnet is a group of compromised systems connected through the internet and controlled by a criminal to perform a malicious activity without authentication and permission. A botnet can compromise the system and steal the data. It can also be used to perform attacks, like Phishing, spamming, and more. To overcome the critical issue, the authors exhibit a novel botnet attack detection approach that could be utilized in fog computing situations to dispense with the attack using the programmable nature of the SDN environment. In order to demonstrate the effectiveness of the proposed technique, extensive experimentation has been performed on the N_BaIoT dataset for botnet attack signature in various edge devices, i.e., Internet of Things (IoT), to evaluate the standard parameters. We have also compared the proposed technique with other deep learning algorithms. The proposed technique shows promising detection accuracy and time utilization results.