AI-Driven Data Analytics for Secure, Privacy-Preserving, and Trustworthy IoT and Sensor Networks

The rapid expansion of Internet of Things (IoT) ecosystems and wireless sensor networks (WSNs) has led to unprecedented volumes of heterogeneous, real-time data generated across smart cities, healthcare, industrial automation, environmental monitoring, and critical infrastructure. Extracting actionable intelligence from this data requires advanced AI-driven analytics capable of operating under strict resource, latency, and scalability constraints.However, the increasing reliance on data-centric IoT architectures introduces significant challenges in security, privacy, and trust. IoT systems are inherently vulnerable due to constrained devices, distributed architectures, heterogeneous communication protocols, and large attack surfaces. Moreover, sensitive data collected from users, industries, and public infrastructure raises serious concerns regarding privacy preservation and regulatory compliance.Artificial Intelligence (AI), including machine learning, deep learning, federated learning, and reinforcement learning, offers transformative opportunities not only for intelligent data analytics but also for adaptive security, anomaly detection, and trust management. Nevertheless, integrating AI with secure and privacy-preserving IoT frameworks remains a critical research challenge.This Research Topic aims to explore innovative solutions at the intersection of:• AI-driven data analytics• Secure and privacy-aware IoT architectures• Trustworthy and resilient sensor networksThe key objective of this Research Topic is to bring together researchers and practitioners to present cutting-edge theoretical and practical contributions that address:• Scalable AI-driven analytics for IoT data streams• Privacy-preserving machine learning in distributed environments• Security-aware data processing architectures• Trust modeling and reputation systems in sensor networks• Resilient and adaptive IoT communication protocolsTo gather further insights in these domains, we welcome articles addressing, but not limited to, the following themes:1. AI-Driven Data Analytics for IoT• Edge AI and fog-based analytics• TinyML for resource-constrained IoT devices• Deep learning for time-series sensor data• Graph neural networks for network optimization• Federated and distributed learning in IoT• Reinforcement learning for adaptive routing and resource allocation• Explainable AI for IoT systems2. Security in IoT and Sensor Networks• AI-based intrusion detection systems• Secure routing and communication protocols• Lightweight cryptographic techniques• Post-quantum cryptography for IoT• Blockchain-enabled IoT security• Zero-trust architectures for sensor networks3. Privacy-Preserving Mechanisms• Differential privacy in IoT data analytics• Secure multi-party computation• Privacy-preserving federated learning• Homomorphic encryption for sensor data• Data anonymization and secure aggregation4. Trust and Resilience• Trust management models for IoT ecosystems• Reputation-based systems in sensor networks• Self-healing and self-organizing IoT systems• Fault tolerance and resilience strategies• Secure and trustworthy AI for critical infrastructure5. Emerging Applications• Smart cities and intelligent transportation systems• Industrial IoT (IIoT) and predictive maintenance• Healthcare IoT and wearable sensor networks• Smart agriculture and environmental monitoring• Smart grids and energy systems Topic editors: Prakasam Periasamy, MD SHOHEL SAYEED, Kousik Nalliyanna Goundar Veerappan Source: https://www.frontiersin.org/research-topics/78923/ai-driven-data-analytics-for-secure-privacy-preserving-and-trustworthy-iot-and-sensor-networks