Abstract

A computer system or network can be disrupted, damaged, or compromised by malware, a sort of harmful program or software. Malware affects many businesses, including financial institutions and the healthcare industry. The existing model of secure healthcare systems uses blockchain-enabled security frameworks to prevent the system from malware attacks by only providing tamper resistance for healthcare networks. Whereas the proposed method is used to identify malware in intelligent healthcare frameworks, a unique method utilizing the Multilayer Perceptron (MLP) algorithm is presented in the proposed system. The proposed approach uses a benchmark Malimg dataset with the families of Dontovo.A, C2Lop.P, Obfuscator.AD, to train a Multilayer Perceptron model to efficiently detect and mitigate malware threats and the implementation of blockchain technology in the proposed model make the healthcare system as a tamper-proof framework renowned for its heightened security, resilience, and decentralized structure which makes it nearly hard to change once recorded without also changing all blocks that come after. The effectiveness of this method in identifying malware attacks with an emphasis on attachments is proven by thorough testing and analysis. The proposed system is improved to existing techniques in terms of accuracy, as demonstrated by a comparative evaluation.