AI4SAFE-IoT: an AI-powered secure architecture for edge layer of Internet of things

Department

Software Engineering and Game Development

Document Type

Article

Publication Date

10-1-2020

Abstract

© 2020, Springer-Verlag London Ltd., part of Springer Nature. With the increasing use of the Internet of things (IoT) in diverse domains, security concerns and IoT threats are constantly rising. The computational and memory limitations of IoT devices have resulted in emerging vulnerabilities in most IoT-run environments. Due to the low processing ability, IoT devices are often not capable of running complex defensive mechanisms. Lack of an architecture for a safer IoT environment is referred to as the most important barrier in developing a secure IoT system. In this paper, we propose a secure architecture for IoT edge layer infrastructure, called AI4SAFE-IoT. This architecture is built upon AI-powered security modules at the edge layer for protecting IoT infrastructure. Cyber threat attribution, intelligent web application firewall, cyber threat hunting, and cyber threat intelligence are the main modules proposed in our architecture. The proposed modules detect, attribute, and further identify the stage of an attack life cycle based on the Cyber Kill Chain model. In the proposed architecture, we define each security module and show its functionality against different threats in real-world applications. Moreover, due to the integration of AI security modules in a different layer of AI4SAFE-IoT, each threat in the edge layer will be handled by its corresponding security module delivered by a service. We compared the proposed architecture with the existing models and discussed our architecture independence of the underlying IoT layer and its comparatively low overhead according to delivering security as service for the edge layer of IoT architecture instead of embed implementation. Overall, we evaluated our proposed architecture based on the IoT service management score. The proposed architecture obtained 84.7 out of 100 which is the highest score among peer IoT edge layer security architectures.

Journal Title

Neural Computing and Applications

Journal ISSN

09410643

Volume

32

Issue

20

First Page

16119

Last Page

16133

Digital Object Identifier (DOI)

10.1007/s00521-020-04772-3

Share

COinS