BlockDLO: Blockchain Computing With Deep Learning Orchestration for Secure Data Communication in IoT Environment

Abstract

Internet of Things (IoT) has more security issues due to the data being shared in an open platform. Integrating blockchain into IoT for security is a new development in computational communication systems. However, attackers are adapting their methods and creating new vulnerabilities in blockchain-based IoT platforms. Furthermore, when the blockchain is integrated with IoT networks, vulnerabilities, privacy issues, and security threats are amplified due to malicious transactions and active attacks. This paper proposes BlockDLO, an approach to IoT security that combines blockchain technology with deep learning. A five-phase architecture is proposed for the edge computing blockchain. In its first phase, network localization is resolved with chaotic map-based identification and authentication. The second phase proposes page rank-based clustering for edge computing. Then, BlockDLO combines the shared-chain technique with a deep distributed file system to address issues with block creation and ledger distribution, and an ethereum smart contract to address data security concerns. The communication route optimization is done with page rank centrality search optimization in its next phase. Finally, the integration of deep learning model to detect malicious data in the IoT network is done using the authenticated received data. BlockDLO creates an efficient intrusion detection system by combining a deep convolution neural network with blockchain. The proposed system is trained using public data sources and tested using an in-house network testbed. The results demonstrate that the proposed system outperforms existing work in terms of energy usage, packet loss rate, end-to-end delay, routing overhead, network lifetime, accuracy, and security strength.

Keywords

• Internet of Things
• blockchain
• deep learning
• data security
• clustering
• search optimization