A Hybrid Machine Learning Intrusion Detection System for Wireless Sensor Networks

Federated Learning (FL) has emerged as a novel distributed Machine Learning (ML) approach, to tackle the challenges associated with data privacy and overload in MLbased intrusion detection systems (IDSs). Drawing inspiration from the FL architecture, we have introduced a hybrid ML IDS tailored for Wireless Sensor Networks (WSNs). This system is crafted to leverage ML for achieving a two-layer intrusion detection mechanism in WSNs free from constraints posed by specific attack types. The architecture follows a server-client model compatible with the configuration of sensor nodes, sink nodes, and gateways in WSNs. In this setup, client models located at sink nodes undergo training using sensing data while the server model at the gateway is trained using network traffic data. This two-layer training approach amplifies the efficiency of intrusion detection and ensures comprehensive network coverage. The results derived from our simulation experiments corroborate the effectiveness of the proposed hybrid ML IDS. It generates precise aggregation predictions and leads to a substantial reduction in redundant data transmissions. Furthermore, the system exhibits efficacy in detecting intrusions through a dual validation process.

I. Introduction

The continuous advancement of WSNs and their associated technologies has led to their widespread application in various industrial sectors. However, WSNs face challenges in countering network attacks due to their inherent limitations. Researchers have proposed various IDSs focusing on identifying suspicious activities through strategies such as anomaly detection and misuse detection [1]. The emergence of ML has offered more possibilities for IDS in WSNs. Leveraging the inherent strengths of ML, these approaches have demonstrated enhanced performance in detecting network attacks, thus becoming a prominent focus in network security research. Through its capacity to train models with extensive relevant data, ML facilitates efficient, highly accurate, and automated risk assessment and intrusion detection [2].