Quantum-Inspired Deep Learning Model for Energy-Efficient Intrusion Detection in Clustered Wireless Sensor Networks

Abstract Wireless Sensor Networks (WSNs) are widely used in critical applications such as environmental monitoring, healthcare systems, and industrial automation. However, the distributed architecture and limited energy resources of sensor nodes make WSNs highly vulnerable to various cyber-attacks, including denial-of-service, sinkhole, and Sybil attacks. Conventional intrusion detection systems primarily focus on improving detection accuracy while neglecting energy efficiency, which is a critical factor affecting network lifetime. To address this limitation, this paper proposes a quantum inspired deep learning framework for energy-efficient intrusion detection in clustered wireless sensor networks. The proposed approach integrates cluster-based communication architecture with a deep neural network optimized using quantum-inspired optimization techniques to enhance intrusion detection performance while minimizing computational and communication overhead. MATLAB based simulations are conducted to evaluate the proposed framework under multiple attack scenarios. Experimental results demonstrate that the proposed method achieves higher detection accuracy, improved precision and recall, and lower energy consumption compared with conventional machine learning based intrusion detection systems. The proposed framework effectively enhances network security while extending the operational lifetime of wireless sensor networks.