Deep learning-enabled anomaly detection for IoT systems

• Published in: Internet of things (Amsterdam. Online) Vol. 21; p. 100656
• Main Authors: Abusitta, Adel, de Carvalho, Glaucio H.S., Wahab, Omar Abdel, Halabi, Talal, Fung, Benjamin C.M., Mamoori, Saja Al
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.04.2023
• Subjects: Artificial intelligence for security; Deep learning; IoT anomaly detection; IoT security; Deep learning; IoT security; Artificial intelligence for security; IoT anomaly detection
• ISSN: 2542-6605; 2542-6605
• DOI: 10.1016/j.iot.2022.100656

Internet of Things (IoT) systems have become an intrinsic technology in various industries and government services. Unfortunately, IoT devices and networks are known to be highly vulnerable to security attacks that target data integrity and service availability. Moreover, the heterogeneity of the data collected from various IoT devices, together with the disturbances incurred within the IoT system, render the detection of anomalous behavior and compromised nodes more challenging compared to traditional Information Technology (IT) networks. As a result, there is a pressing need for effective and reliable anomaly detection to identify malicious data to guarantee that they will not be used in IoT-driven decision support systems. In this paper, we propose a deep learning-powered anomaly detection for IoT that can learn and capture robust and useful features, which cannot be significantly affected by unstable environments. These features are then used by the classifier to enhance the accuracy of detecting malicious IoT data. More specifically, the proposed deep learning model is designed based on a denoising autoencoder, which is adopted to obtain features that are robust against the heterogeneous environment of IoT. Experimental results based on real-life IoT datasets show the effectiveness of the proposed framework in terms of enhancing the accuracy of detecting malicious data compared to the state-of-the-art IoT-based anomaly detection models.