Intelligent blockchain based attack detection framework for cross-chain transaction

The online trading market has been greatly improved by the significance of Cross-Chain (CC) transactions. However, malicious events are the chief threat to offering secure cross-chain transactions; several crypto security models have been executed in the past to enrich the CC transaction process. However, those models cannot provide secure CC data because of malicious harm. So, the current report aimed to implement a novel Elman Neural-based CAST Blockchain Framework (ENbCBF) to gain a secure CC platform. Firstly, the malicious prediction functions were executed to maintain the CC's confidential score. Consequently, the transaction process was begun in the Ethereum blockchain environment. Hence, the planned novel secure CC design is validated in the etherscan Python environment. The User needs to decide the transaction amount types; the Elman neural function continuously afforded the attack recognition process, resulting in less time complexity by avoiding the delay. Hence, the reported high malicious event recognition exactness and less processing time for the transaction and crypto process than conventional studies.