Reducing computational cost in IoT cyber security: case study of artificial immune system algorithm.

Zakariyya, Idris; Al-Kadri, M. Omar; Kalutarage, Harsha; Petrovski, Andrei

Abstract

Using Machine Learning (ML) for Internet of Things (IoT) security monitoring is a challenge. This is due to their resource constraint nature that limits the deployment of resource-hungry monitoring algorithms. Therefore, the aim of this paper is to investigate resource consumption reduction of ML algorithms in IoT security monitoring. This paper starts with an empirical analysis of resource consumption of Artificial Immune System (AIS) algorithm, and then employs carefully selected feature reduction techniques to reduce the computational cost of running the algorithm. The proposed approach significantly reduces computational cost as illustrated in the paper. We validate our results using two benchmarks and one purposefully simulated data set.

Citation

ZAKARIYYA, I., AL-KADRI, M.O., KALUTARGE, H. and PETROVSKI, A. 2019. Reducing computational cost in IoT cyber security: case study of artificial immune system algorithm. In Obaidat, M. and Samarati, P. (eds.) Proceedings of the 16th International security and cryptography conference (SECRYPT 2019), co-located with the 16th International joint conference on e-business and telecommunications (ICETE 2019), 26-28 July 2019, Prague, Czech Republic. Setúbal, Portugal: SciTePress [online], 2, pages 523-528. Available from: https://doi.org/10.5220/0008119205230528.

• Conference Name: 16th International security and cryptography conference (SECRYPT 2019)
• Conference Location: Prague, Czech Republic
• Start Date: Jul 26, 2019
• End Date: Jul 28, 2019
• Acceptance Date: May 2, 2019
• Online Publication Date: Oct 24, 2019
• Publication Date: Oct 31, 2019
• Deposit Date: Aug 29, 2019
• Publicly Available Date: Aug 29, 2019
• Publisher: SciTePress
• Volume: 2
• Pages: 523-528
• ISBN: 9789897583780
• DOI: https://doi.org/10.5220/0008119205230528
• Keywords: Computational cost; IoT security; Feature reduction; Resource consumption; Machine learning
• Public URL: https://rgu-repository.worktribe.com/output/401052