A Comprehensive Review of Malicious Node Detection with Cross-Attention Vision Transformers and Blockchain-Based Distributed Data Storage in Wireless Sensor Networks

Abstract

Wireless Sensor Networks (WSNs) are widely deployed in critical applications such as environmental monitoring, healthcare, and smart cities. However, their distributed and resource-constrained nature makes them highly vulnerable to malicious node attacks, data tampering, and routing disruptions. Recent advancements integrate deep learning and blockchain technologies to enhance network security and reliability. In particular, cross-attention Vision Transformers (ViTs) have emerged as powerful tools for feature extraction and anomaly detection due to their ability to model long-range dependencies. Vision Transformer architectures process sensor data representations efficiently and outperform traditional convolution-based models. Simultaneously, blockchain-based distributed storage ensures data integrity, authentication, and decentralization, mitigating risks associated with centralized systems.

This paper presents a comprehensive review of malicious node detection techniques in WSNs, focusing on the integration of cross-attention Vision Transformers and blockchain frameworks. It analyzes recent developments between 2020 and 2023, highlighting hybrid approaches combining machine learning, trust management, and decentralized storage. Furthermore, a comparative analysis of various models is provided based on detection accuracy, computational efficiency, scalability, and security robustness. The review also discusses current challenges such as energy consumption, model complexity, and real-time deployment constraints. Finally, future research directions are outlined to enable secure, efficient, and intelligent WSN infrastructures.