Optimized common features selection and deep-autoencoder (OCFSDA) for lightweight intrusion detection in Internet of things.

Otokwala, Uneneibotejit; Petrovski, Andrei; Kalutarage, Harsha

Abstract

Embedded systems, including the Internet of Things (IoT), play a crucial role in the functioning of critical infrastructure. However, these devices face significant challenges such as memory footprint, technical challenges, privacy concerns, performance trade-offs and vulnerability to cyber-attacks. One approach to address these concerns is minimising computational overhead and adopting lightweight intrusion detection techniques. In this study, we propose a highly efficient model called Optimized Common Features Selection and Deep-Autoencoder (OCFSDA) for lightweight intrusion detection in IoT environments. The proposed OCFSDA model incorporates feature selection, data compression, pruning and deparameterization. We deployed the model on a Raspberry Pi4 using the TFLite interpreter by leveraging optimisation and inferencing with semi-supervised learning. Using the MQTT-IoT-IDS2020 and CICIDS2017 datasets, our experimental results demonstrate a remarkable reduction in the computation cost in terms of time and memory use. Notably, the model achieved an overall average accuracies of 99% and 97%, along with comparable performance on other important metrics such as precision, recall and F1-score. Moreover, the model accomplished the classification tasks within 0.30 and 0.12s using only 2KB of memory.

Citation

OTOKWALA, U., PETROVSKI, A. and KALUTARAGE, H. [2024]. Optimized common features selection and deep-autoencoder (OCFSDA) for lightweight intrusion detection in Internet of things. International journal of information security [online], Latest Articles. Available from: https://doi.org/10.1007/s10207-024-00855-7

• Journal Article Type: Article
• Acceptance Date: Apr 26, 2024
• Online Publication Date: Apr 30, 2024
• Deposit Date: Apr 30, 2024
• Publicly Available Date: Apr 30, 2024
• Journal: International journal of information security
• Print ISSN: 1615-5262
• Electronic ISSN: 1615-5270
• Publisher: N&N Global Technology
• Peer Reviewed: Peer Reviewed
• DOI: https://doi.org/10.1007/s10207-024-00855-7
• Keywords: Systems security; Network security; Intrusion detection; Internet of Things (IoT); Feature selection; Computational cost
• Public URL: https://rgu-repository.worktribe.com/output/2312008