Source of Publication
Applied Sciences (Switzerland)
© 2019 by the authors. Fog computing is a paradigm that extends cloud computing and services to the edge of the network in order to address the inherent problems of the cloud, such as latency and lack of mobility support and location-awareness. The fog is a decentralized platform capable of operating and processing data locally and can be installed in heterogeneous hardware which makes it ideal for Internet of Things (IoT) applications. Intrusion Detection Systems (IDSs) are an integral part of any security system for fog and IoT networks to ensure the quality of service. Due to the resource limitations of fog and IoT devices, lightweight IDS is highly desirable. In this paper, we present a lightweight IDS based on a vector space representation using a Multilayer Perceptron (MLP) model. We evaluated the presented IDS against the Australian Defense Force Academy Linux Dataset (ADFA-LD) and Australian Defense Force AcademyWindows Dataset (ADFA-WD), which are new generation system calls datasets that contain exploits and attacks on various applications. The simulation shows that by using a single hidden layer and a small number of nodes, we are able to achieve a 94% Accuracy, 95% Recall, and 92% F1-Measure in ADFA-LD and 74% Accuracy, 74% Recall, and 74% F1-Measure in ADFA-WD. The performance is evaluated using a Raspberry Pi.
Physical Sciences and Mathematics
Fog computing, Intrusion detection, IoT security, Multilayer Perceptron
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Khater, Belal Sudqi; Wahab, Ainuddin Wahid Bin Abdul; Idris, Mohd Yamani Idna Bin; Hussain, Mohammed Abdulla; and Ibrahim, Ashraf Ahmed, "A lightweight perceptron-based intrusion detection system for fog computing" (2019). All Works. 148.
Indexed in Scopus
Open Access Type
Gold: This publication is openly available in an open access journal/series