Abstract—The premise of the Internet of Things (IoT) is to connect not only computers and mobile devices, but also interconnect smart buildings, homes, and cities, as well as electrical and water grids, automobiles, and airplanes just to mention some examples. IoT leads to the development of a wide range of advanced information services that are pervasive, cost-effective, and can be accessed from anywhere and at any time. In this paper we present a multilayer architecture to integrate devices to the IoT, making it available from everywhere at any time. However, with the introduction of IoT we will be experiencing grand challenges to secure and protect its advanced information services due to the significant increase of the attack surface, complexity, heterogeneity, and number of interconnected resources. In order to deal with such challenges, we introduce an IoT Framework to build trustworthy and secure IoT applications and services. The framework enables developers to consider security issues at all IoT layers and integrate security algorithms with the functions and services offered in each layer instead of considering security in an ad-hoc and after thought manner. We show the applicability of our methodology to secure and protect IoT end nodes providing them with the capabilities for self-monitoring and self-recovering after an external event has occurred.
Index Terms—Internet of things, access control, threat detection, neural networks.
Jesus Pacheco and Victor H. Benitez are with the Universidad de Sonora, Blvd. Luis Encinas y Rosales, Col. Centro, Hermosillo, Sonora 83103, Mexico (e-mail: {jpacheco,vbenitez}@ industrial.uson.mx).
Zhiwen Pan is with Chinese Academy of Science, Beijing, China (e-mail: pzw@ict.ac.cn).
Cite: Jesus Pacheco, Victor H. Benitez, and Zhiwen Pan, "Security Framework for IoT End Nodes with Neural Networks," International Journal of Machine Learning and Computing vol. 9, no. 4, pp. 381-386, 2019.
Copyright © 2019 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).