Securing Wireless Sensor Networks Against DoS attacks in Industrial 4.0

Abstract

Wireless Sensor Networks (WSNs) play a vital role in Industrial 4.0 by facilitating significant data collection for monitoring and control purposes. However, their distributed and resource-constrained nature makes WSNs vulnerable to Denial-of-Service (DoS) attacks, which can impede their normal operation and jeopardize their functionality. To address this issue, we propose a new machine learning (ML) approach that enhances the security of WSNs against DoS attacks in Industrial 4.0. Our approach incorporates a spatial learning unit, which captures the positional information in WSN traffic flows, and a temporal learning unit which captures time interdependency features within periods of traffic flows. To evaluate the proposed approach, we tested it on a publicly available dataset. The results demonstrate that it achieves a high detection rate while maintaining a low false alarm rate. Moreover, our Intrusion Detection System (IDS) exhibits good scalability and robustness against various DoS attacks. Our approach provides a reliable and effective solution to secure WSNs in Industrial 4.0 against DoS attacks and can be further developed and tested in various real-world scenarios.