A Survey of Methods and Architectures for Malicious Node Detection with Cross Attention Vision Transformers and Blockchain-Based Distributed Data Storage in Wireless Sensor Networks

Abstract

Wireless Sensor Networks (WSNs) play a crucial role in modern distributed systems, supporting applications such as smart cities, healthcare, and industrial automation. However, their decentralized and resource-constrained nature makes them highly vulnerable to malicious node attacks, including data manipulation, packet dropping, and routing disruption. Traditional detection techniques based on rule-based or statistical methods are inadequate for handling dynamic and complex attack patterns. Recent advancements in Artificial Intelligence (AI), particularly Vision Transformers (ViTs) with cross-attention mechanisms, have significantly improved malicious node detection by capturing global dependencies and contextual relationships in network data. Simultaneously, blockchain technology has emerged as a robust solution for secure, decentralized, and tamper-proof data storage in WSNs. Blockchain-based WSN architectures enhance data integrity, transparency, and trust through distributed ledgers and smart contracts. Studies show that blockchain-integrated detection frameworks can achieve near-perfect classification accuracy while ensuring secure data transmission. Furthermore, hybrid AI-blockchain systems combine intelligent detection with secure storage, improving resilience against attacks. This survey reviews recent methods, compares architectures, identifies research gaps, and highlights future directions for developing secure and scalable WSN systems.