Two level blockchain-based privacy preservation framework in IoT with heuristic fusion mechanism-aided deep learning architecture

Abstract

The Internet of Things (IoT) connects more objects used in the modern world. To connect IoT nodes, it needs maintenance services, robustness, frictionless authentication, and high security. Blockchain emerges as a workable solution by providing those important features. Several authentication problems, maintenance, and security with IoT systems are solved because of blockchain technology. The blockchain-based IoT network is an open source, and everyone may see encrypted keys and transactional information. So, from this public network, anyone can take crucial information about users. A new blockchain-adopted IoT-based privacy preservation approach is developed to provide higher security with less utilization of the cost requirements. Here, two levels of data privacy is accomplished by utilizing the deep learning approach. The first level of privacy is used for authenticating a person, where the authentication among collected data is performed using Modified Adaboost and Long Short-Term Memory (MABLSTM), and the authenticated data is stored in the blockchain database. After that, the second level of privacy is obtained by performing data encoding with the encoder part of Autoencoder, and further Elliptic Curve Cryptography (ECC) is used to encrypt the data. Hence, the encrypted data is given to the data decryption process, and this has been subjected to the decoder part of the autoencoder to reconstruct the original data. Moreover, the parameters in the autoencoder and the parameters within the MABLSTM are optimized with the help of the developed Modified Levy Flight Distribution with Grasshopper Optimization (MLFD-GO). However, the parameters like LSTM and Adaboost are optimized with the help of the MLFD-GO algorithm to enhance the performance in terms of accuracy and precision for providing the higher level authentication scheme to provide high level security. Finally, the performance of the developed blockchain-based privacy preservation approach is validated over recently developed techniques.