This research contributes a novel, energy-efficient, and scalable architecture for industrial data protection, setting a foundation for future integration with 6G-enabled IIoT systems, federated trust networks, and lightweight transformer-based threat detection frameworks.
Abstract
The growing interconnectivity of industrial systems has intensified the need for secure, intelligent, and scalable data transfer mechanisms within Industrial Internet of Things (IIoT) environments. Despite rapid IIoT adoption, industrial data transfer remains vulnerable to high-volume, dynamic cyber anomalies and consensus-level attacks, while existing security mechanisms struggle to jointly deliver low-latency, scalable, and trustworthy communication under large-scale adversarial deployments. This study introduces a Secure Dual-Consensus Blockchain-Enabled Deep Learning Framework (SD-BDL) that unifies blockchain security and adaptive anomaly detection to ensure trustworthy and efficient IIoT communication. The framework employs a hybrid consensus mechanism, integrating Delegated Proof of Stake (DPoS) and Practical Byzantine Fault Tolerance (PBFT) to achieve enhanced fault tolerance, reduced latency, and protection against collusion and Sybil attacks. To address the dynamic and high-volume nature of IIoT data streams, a CNN–LSTM model is deployed for real-time anomaly detection, with hyperparameters optimized using the Adaptive Aquila Optimization (AAO) algorithm—identified as the most effective technique for achieving rapid convergence, high detection accuracy, and balanced exploration–exploitation. The proposed SD-BDL framework is evaluated on an IIoT dataset, incorporating preprocessing steps to mitigate class imbalance, missing values, and noise interference. Experimental outcomes demonstrate a significant improvement in performance metrics, achieving an R² score of 0.985, throughput enhancement of 25.2%, and latency reduction of 19.4% compared with benchmark models using PSO, GA, and Bayesian optimization. The hybrid consensus blockchain further ensures transaction integrity, tamper resistance, and low-energy overhead, validating its robustness under adversarial and large-scale deployment scenarios involving over 1,000 nodes. This research contributes a novel, energy-efficient, and scalable architecture for industrial data protection, setting a foundation for future integration with 6G-enabled IIoT systems, federated trust networks, and lightweight transformer-based threat detection frameworks.
The proposed hybrid approach outperforms ML-only and blockchain-only baselines, offering a scalable, secure, and real-time IDS for IIoT infrastructures.
Industrial Internet of Things (IIoT) systems require dynamical, safe, and competent control to address the dynamic industrial processes. Centralized Deep Reinforcement Learning (DRL) methods are however vulnerable to privacy, high communication overheads, and model tampering. In order to address these shortcomings, the present paper suggests a Blockchain-Secured Federated Deep Reinforcement Learning (BS-FDRL) system to privacy-guaranteed and resilient IIoT control. The suggested system has distributed edge agents, which locally train DRL models and exchange only encrypted policy updates through federated learning; this guarantees the privacy of data. A smart contract-based blockchain layer allows aggregation and safe validation of model parameters to be tampered with. Also, differential privacy is integrated to safeguard sensitive industrial data in the process of policy exchange. The framework is coded with Python 3.10, DDPG/PPO algorithms with PyTorch, Flower to coordinate federated, and Hyperledger Fabric to integrate with blockchains. Industrial control and anomaly detection experimental analyses show that performance improvements are significant. The increase in the cumulative reward of the proposed model is 18-22% and the convergence rate is about 28 times higher than the baseline approaches. Stability of control is improved to 91.3% and communication overhead is cut down by up to 25%. Moreover, the overall energy consumption is reduced by approximately 65%, which enhances the efficiency of the system. Security analysis indicates a 96% poisoning attack detection and 94% inference attack resistance. The system is robust and only 35% accuracy deteriorates in adverse conditions. The results prove that BS-FDRL offers scalable, secure, and efficient communication-based intelligent control in Industry 4.0 IIoT setups.
A.Mallika, Anitha Christy, P. Krishnamoorthy et al.· 2026 6th International Confe...· 0 citations
BELS-IoT is proposed, a novel decentralized protection architecture that integrates a cryptocurrency-based blockchain layer with a multi-layer ensemble learning engine that rewards honest behavior and penalizes malicious activities while maintaining privacy through federated learning with blockchain-verified reputation scores.
Anwar Kalghoum, Leila Azouz Saidane· SN Computer Science· 0 citations
The study proposes a secure and adaptive intrusion detection model using Federated Learning and Blockchain, augmented with autoencoder-based feature reduction, showing that combining FL, blockchain, and deep feature extraction offers a viable and secure solution for intrusion detection systems in IoT.
Tahseen A. Wotaifi· Journal of Intelligent Infor...· 0 citations
This paper introduces Data Communities as a novel paradigm for privacy-preserving, blockchain-enabled cooperative digital infrastructures, formalized within the Cooperative Digital Infrastructure (CDI) framework and formalizes privacy guarantees through an adversarial model encompassing classical, quantum, insider, and governance-level threats.
The growth of the Internet of Things (IoT) has brought about security concerns owing to the massive global integration of diverse and constrained devices. Blockchain, Machine Learning (ML) and Deep Learning (DL) techniques have been proposed as effective ways to improve IoT security. This paper reviews the literature on the use of blockchain and smart learning techniques for security enhancement and threat detection in IoT networks. Blockchain offers a decentralized and immutable approach to secure data integrity, authenticating and controlling access to IoT devices, while ML and DL techniques allow intelligent monitoring of network data to detect anomalies and predict cyber-attacks. This study follows a systematic literature review approach, examining peer-reviewed journal articles and conference proceedings from 2019 to 2024. The analysis shows while blockchain, ML and DL technologies play a crucial role in enhancing IoT security, they each have limitations including scalability, computational overhead, data dependency and lack of flexibility against new cyber threats. Additionally, the majority of studies concentrate on either blockchain-based security or ML-based intrusion detection, with limited study on the integration of the two for real-time threat detection and mitigation. The study highlights this limitation and calls for the development of intelligent hybrid models that integrate blockchain technology with ML/DL to address scalability, adaptability and real-time security for IoT networks to ensure confidentiality, integrity and reliability.
Shamsudeen Mohammed S, Nwobodo-Nzeribe Nnenna Harmony, Aghaizu Herman Chijioke· International journal of re...· 0 citations