English

Abstract

One of the major technologies in delivering infrastructure and data service requirements at low cost and with minimal effort is Cloud Computing (CC), which has been implemented in several aspects of the IT industry. Since the rapid growth of CC has been observed, there is still an information security concern that intruders completely attack. With the potential of being practised in various utilizations, blockchain can be implemented in several cloud service providers. Blockchain platform has basically performed a large computation quantity which doesn’t accomplish the practical purpose of building Proof of Work (PoW) with context awareness accord from decentralized participants. Long Short-Term Memory (LSTM)has been designed particularly for overcoming the long-term dependency issues faced by Recurrent Neural Networks (RNN). This paper focuses on a novel consensus mechanism by LSTM which consists of feedback connections in making a difference with several conventional feed-forward Neural Networks. The research directed computation spent to consensus towards RNN optimization for better cyber security in blockchain implemented in the cloud platform. However, the enormous amount of data involved in the blockchain has been trained through the LSTM model that supports serving learning proof through cell states which handle the network of current long-term memory. Therefore, Contextual Identity Management (CAIM) mechanism is adopted through the LSTM model in blockchain for various Cloud Service Provider(CSP) in unifying the contextual details with the process of identity management that generate the probable robust solution. This assists in creating better decisions with respect to policy, authentication, routing and authorization for recent interacted data. Moreover, the proposed LSTM model in blockchain has been compared with the existing cyber-secured model of blockchain to determine the efficiency of the cyber-secured model of blockchain in the cloud platform.