An Intelligent Secure Monitoring Phase in Blockchain Framework for Large Transaction

Abstract

Blockchain is the key concept for security purposes for digital applications. But, in some cases, the effectiveness of the malicious behavior has degraded the security function of the blockchain. So, to enrich the blockchain process prediction and to neglect the malicious event from the data broadcasting medium is very important. So, the current research article intends to develop an efficient monitoring strategy based on incorporating deep features. Hence, the designed paradigm is termed as Lion-based Convolutional Neural Model (LbCNM) with serpent encryption. Before performing the encryption process, the novel LbCNM parameters have been activated to monitor the data process channel in the blockchain environment. Here, the malicious behaviors were estimated by incorporating the known and unknown user behavior in the Lion fitness model. During the execution, the fitness formulation of Lion is acted in the classification layer of the convolutional model. Once the present malicious characteristics have been detected, it is neglected from the data broadcasting channel. Hereafter, the transactional data has been encrypted and stored in the specific cloud. The planned strategy is verified in the python platform. The successful performance of the LbCNM with serpent has been analyzed with some key parameters like confidential rate, accuracy, data overhead, and processing time.