Abstract
The IoT devices has brought challenges in the area of information security. They have power restrictions and usually use the MQTT and CoAP protocols in plain text. This contributes to these devices being targets of malicious actions or used to attack other smart objects. Consequently, energy-efficient intrusion detection systems and procedures are essential in networks with IoT devices. An alternative for this are detection solutions based on the distribution of processing between devices in the same network domain with an artificial intelligence layer. Therefore, this article analyzed six possible algorithms (Logistic Regression, k-Nearest Neighbours, Gaussian Naive Bayes, Decision Trees, Random Forests and Linear Support Vector Machine) for the AI layer. The analysis measured the capabilities of the algorithms to identify attacks on CoAP and MQTT networks, considering the synthetic traffic of unidirectional and bidirectional flows. The metrics used were the following: energy consumption of hardware components (CPU, RAM, Package and GPU), execution time, precision, accuracy, recall and F1-Score. Finally, it was identified that the bidirectional flow is the type of traffic that was identified with greater precision and the MQTT attack was better identified by the algorithms.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Oliveira, L.P., Vieira, M.N., Leite, G.B., de Almeida, E.L.V.: Evaluating energy efficiency and security for internet of things: a systematic review. In: Barolli, L., Amato, F., Moscato, F., Enokido, T., Takizawa, M. (eds.) AINA 2020. AISC, vol. 1151, pp. 217–228. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-44041-1_20
Naik, N.: Choice of effective messaging protocols for IoT systems: MQTT, CoAP, AMQP and HTTP. In: ISSE (2017). https://doi.org/10.1109/SysEng.2017.8088251
Suarez, J., Vidal, I., Garcia-Reinoso, J., Valera, F., Azcorra, A.: Exploring the use of RPAs as 5G points of presence. In: European Conference on Networks and Communications (EuCNC), pp. 27–31 (2016). https://doi.org/10.1109/EuCNC.2016.7560998
Metongnon, L., Sadre, R.: Beyond telnet: prevalence of IoT protocols in telescope and honeypot measurements. In: Proceedings of the 2018 Workshop on Traffic Measurements for Cybersecurity, pp. 21–26 (2018)
Allahyari, M., et al.: A brief survey of text mining: classification, clustering and extraction techniques. arXiv preprint arXiv:1707.02919 (2017)
Aljawarneh, S., Aldwairi, M., Yassein, M.B.: Anomaly-based intrusion detection system through feature selection analysis and building hybrid efficient model. J. Computat. Sci. 25, 152–160 (2018). Elsevier
Biswas, S.K., et al.: Intrusion detection using machine learning: a comparison study. Int. J. Pure Appl. Math. 118(19), 101–114 (2018)
Oliveira, L.P., Sadok, D.F.H.: ProNet framework: network management using semantics and collaboration. In: INCOS (2013). https://doi.org/10.1109/INCoS.2013.78
Oliveira, L.P., et al.: Deep learning library performance analysis on raspberry (IoT device). In: Barolli, L., Woungang, I., Enokido, T. (eds.) AINA 2021. LNNS, vol. 225, pp. 383–392. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-75100-5_33
Migliardi, M., Merlo, A.: Modeling the energy consumption of distributed ids: a step towards green security. In: 2011 Proceedings of the International Convention MIPRO. IEEE (2011)
Oliveira, L., Hadj, S.D., Gonçalves, G., Abreu, R., Kelner, J.: Collaborative algorithm with a green touch. In: Sénac, P., Ott, M., Seneviratne, A. (eds.) MobiQuitous 2010. LNICS, SITE, vol. 73, pp. 51–62. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-29154-8_5
Hindy, H., Bayne, E., Bures, M., Atkinson, R., Tachtatzis, C., Bellekens, X.: Machine learning based IoT intrusion detection system: an MQTT case study (MQTT-IoT-IDS2020 dataset). In: Ghita, B., Shiaeles, S. (eds.) INC 2020. LNNS, vol. 180, pp. 73–84. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-64758-2_6
Batista, G.E.d.A.P., et al.: Pré-processamento de dados em aprendizado de máquina supervisionado. Ph.D. thesis - Universidade de São Paulo (2003)
Acknowledgments
The authors would like to thank the Federal Institute of Paraíba(IFPB)/Campus João Pessoa for financially supporting the presentation of this research and, especially thank you, to the IFPB Interconnect Notice - No. 02/2021.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Vieira, M.N., Oliveira, L.P., Carneiro, L. (2022). A Comparative Analysis of Machine Learning Algorithms for Distributed Intrusion Detection in IoT Networks. In: Barolli, L., Hussain, F., Enokido, T. (eds) Advanced Information Networking and Applications. AINA 2022. Lecture Notes in Networks and Systems, vol 449. Springer, Cham. https://doi.org/10.1007/978-3-030-99584-3_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-99584-3_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-99583-6
Online ISBN: 978-3-030-99584-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)