The internet of things, or IoT, is a system or structure of interconnected computing devices, mechanical and digital machines, objects, animals or people that are provided with unique identifiers (UIDs) and have the capability to communicate over a system of connections without demanding humanto-human or human-to-computer collaboration. Wireless Sensor Networks (WSNs) are main ingredients of the IoT. Both the IoT and WSNs have many critical and non-critical applications that interrelate almost every element of our modernized life ensuing in efficiency improvements, economic profits, and reduced human exertions. Unfortunately, Cybersecurity continues to be a serious and deliberate matter for any sector in the cyberspace as the sum of security breaches is widening unceasingly. It is acknowledged that thousands of zero-day attacks are incessantly emerging because of the addition of various protocols principally from Internet of Things (IoT) [1]. One of the top considerable security flaws experienced by WSNs is denial of service (DoS) which can even lead to the breakdown of the complete system or to wrong decisions being made by the system that can cause adverse results. Furthermore, the resource limitations of the devices used in these networks complicate the problem. Machine learning, Deep learning and Data mining advanced techniques evolve many solutions to secure IoT and WSNs. In this paper, we survey and compare the performance and effectiveness of each technique developed to counter mainly DOS attacks.

Published in: Internet Technology and Secured Transactions (ICITST-2018)

• Date of Conference: 10-13 December 2018
• DOI: 10.2053/ICITST.WorldCIS.WCST.WCICSS.2018.0011
• ISBN: 978-1-908320-94-0
• Conference Location: University of Cambridge, Churchill College