Performance Analysis and Comparison of Detecting DoS Attacks In IoT using Machine Learning, Deep Learning and Data Mining: a survey

Kassem Ahmad, Hussein Ramadan, Mohammed Elhajj, Jihad Hamieh

Research output: Contribution to conferencePaperpeer-review

57 Downloads (Pure)

Abstract

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.
Original languageEnglish
Number of pages9
Publication statusPublished - 2018
Externally publishedYes
Event13th IEEE International Conference for Internet Technology and Secured Transactions, ICITST 2018 - University of Cambridge, Churchill College, London
Duration: 10 Dec 201813 Dec 2018
Conference number: 13

Conference

Conference13th IEEE International Conference for Internet Technology and Secured Transactions, ICITST 2018
Abbreviated titleICITST
CityLondon
Period10/12/1813/12/18

Fingerprint

Dive into the research topics of 'Performance Analysis and Comparison of Detecting DoS Attacks In IoT using Machine Learning, Deep Learning and Data Mining: a survey'. Together they form a unique fingerprint.

Cite this