The continuous digitization of the modern farming sector demands secure, intelligent, privacy-preserving, and scalable infrastructures for real-time data analysis. However, existing smart farming systems face significant challenges, including cyberthreats, data authenticity issues, and the need for reliable decision support. This article proposes a secure Digital Twin (DT) architecture for smart agriculture recommendation systems, integrated with Blockchain and Federated Gated Recurrent Units (FGRU). At the perception layer, IoT sensors monitor soil, crop, and environmental data, which is gathered by a Request Control Authority (RCA) and transmitted to local models. To ensure privacy, a GRU-based Federated Learning (FL) approach is employed to detect cyberattacks—such as Sybil, Man-in-the-Middle (MITM), DDoS, and Replay attacks—without exposing raw decentralized data. Furthermore, a Blockchain-assisted Zero-Knowledge Proof-based Authority (ZKPA) mechanism is integrated to ensure data authenticity. The validated farming data is stored at the architecture’s final layer, enabling a Physical Twin to monitor real-time processes and generate precise recommendations. The architecture was evaluated using a paddy field dataset (26 features, 10,081 samples). Experimental results show that the proposed federated GRU model achieves perfect detection performance for all considered attacks, while the ZKPA-based authentication mechanism achieves a 98–99% authentication success rate with sub-10 ms verification time and only 15–25% additional computational overhead, which is better than existing works.

Smart farming influences advanced technologies to optimize agricultural procedures, yet it meets significant cybersecurity challenges, particularly in external intrusion detection (EID). This article proposes a novel architecture combining blockchain technology and federated learning (FL) to reinforce the security of smart farming systems (SMSs) against external threats. The integration of blockchain ensures data authentication and transparent data storage, while FL enables collaborative model training without compromising data privacy. Our architecture employs ensemble learning (EL) for the local model at the ensemble layer to train each smart land’s data and offers privacy-prevented security. These devices utilize FL techniques to collaboratively train intrusion detection models while preserving the confidentiality of sensitive data. The aggregated model completes data aggregation at the authentication layer, and the Proof of Authentication Consensus Algorithm is leveraged for smart land’s data authentication. The Internet of Things Sensor device’s identical information of smart lands is stored at the macro base stations (MBSs). After downloading the aggregated values of the aggregated model, the local model transfers the smart lands information to the Cloud layer for decision making and decentralized storage. The validation outcomes of the proposed architecture demonstrate excellent performance, with an average processing time of 3.663 s and 0.9956 accuracy for smart land compared to existing frameworks.

Smart Classrooms (SCR) are reshaping the learning experience with their interactive technology and personalized knowledge, leading to improved student engagement by seamlessly integrating digital gadgets. In this rapidly evolving landscape, the integrity and efficiency of Heating, Ventilation, and Air Conditioning (HVAC) systems are essential to the futuristic student’s life. This paper introduces SuRaksha: AI-Powered Blockchain Framework for HVAC Tamper Detection and Authentication in Smart Classrooms. Leveraging the power of ensemble learning (EL) at the intelligent and connection layer of the proposed framework, our approach employs IoT sensors to collect comprehensive data from HVAC appliances. The EL algorithms then analyze the collected data to detect any instances of tampering in real-time. At the security layer, robust authentication mechanisms are implemented to verify the integrity of the HVAC data before securely storing it on the cloud. This multi-layered framework enhances the detection and authentication processes and ensures the reliability and security of HVAC operations in intelligent classroom environments. Extensive experiments and validations demonstrate the efficacy of the proposed framework in identifying tampering incidents and providing a secure, authenticated, and reliable system for modern educational facilities. The validation outcomes of the proposed framework demonstrate excellent performance, with an average processing time of 3.725 Secs and 99.84% accuracy for Smart Classrooms compared to existing works.

Cybersecurity has become an inevitable concern in the healthcare industry due to the rapid growth of the Internet of Health Things (IoHT). The IoHT is revolutionizing healthcare by enabling remote access to hospital equipment, real-time patient monitoring, and urgent alerts to patients and hospitals. However, the convenience of these systems also makes them vulnerable to cyberattacks, with hackers seeking to disrupt health services or extort money through ransomware attacks. Efficiently detecting multiple threats is a challenging task because IoHT generates large temporal data and system log information. In this paper, we propose time series classification models for the identification of potential cyberattacks in IoHT networks. First, we introduce Neighborhood Component Analysis (NCA) with modifications of the regularization parameter to select the vital input features. With the selected features, we propose two LSTM-based models: Directed Acyclic Graph-based Long Short-Term Memory (DAG-LSTM) and Projected Layer-based Long Short-Term Memory (PL-LSTM) for detecting cyberattacks. We evaluate the existing time series classification models (i.e., GRU, LSTM, and Bi-LSTM) and proposed models (i.e., DAG-LSTM and PL-LSTM) using real-world IoHT data. We also validate the models by applying a non-parametric statistical test, Friedman test. Our evaluation results show that the proposed DAG-LSTM achieves the highest accuracy with 99.89% training and 92.04% an average testing accuracy.

In recent years, the Internet of Things (IoT) and enterprise management systems (EMS) have been rapidly growing and applied in advanced Industries. It provides better big data analytics and the most promising computing platforms. Moreover, IoT is transforming into the augmented intelligence of things (AIoT), developing a human-oriented paradigm for enterprises with AI. Still, smart enterprises and industries have additional requirements, such as device and data trust, robust decision-making, communication latency, and secure data storage. However, previous emerging paradigms and approaches did not fully address all of the aforementioned requirements. Therefore, this article proposes a blockchain-based trust management scheme for smart enterprises with augmented intelligence. The blockchain-based device trust authentication mechanism is used at the device connection layer for device authentication in clusters of IoT devices (smart enterprises branch-SEB). Furthermore, the blockchain-based augmented intelligence enabled approach is leveraged for data authentication at the authentication layer. Finally, smart enterprise data are stored in the distributed hash table (DHTs) and decentralized cloud layer with distributed hash table. We evaluated the proposed scheme using qualitative and quantitative analysis and compared it to the existing studies, showing better performance as 40.887-ms computational cost and 1872-bits transactional cost.