Biserial Miyaguchi–Preneel Blockchain-Based Ruzicka-Indexed Deep Perceptive Learning for Malware Detection in IoMT

• Published in: Sensors (Basel, Switzerland) Switzerland), 2021-10, Vol.21 (21), p.7119
• Main Author: Alotaibi, Abdullah Shawan
• Format: Article
• Language: English
• Subjects: Accuracy; Application programming interface; Blockchain; Business metrics; Classification; Correlation coefficients; deep multilayer perceptive learning; Feature selection; internet of medical things (IoMT); Internet of Things; Machine learning; Malware; malware detection; Medical research; Miyaguchi-Preneel cryptographic hash-based blockchain; Multilayers; Neural networks; point biserial correlation; Privacy; Ruzika index; Software; Support vector machines
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s21217119

Detection of unknown malware and its variants remains both an operational and a research challenge in the Internet of Things (IoT). The Internet of Medical Things (IoMT) is a particular type of IoT network which deals with communication through smart healthcare (medical) devices. One of the prevailing problems currently facing IoMT solutions is security and privacy vulnerability. Previous malware detection methods have failed to provide security and privacy. In order to overcome this issue, the current study introduces a novel technique called biserial correlative Miyaguchi–Preneel blockchain-based Ruzicka-index deep multilayer perceptive learning (BCMPB-RIDMPL). The present research aims to improve the accuracy of malware detection and minimizes time consumption. The current study combines the advantages of machine-learning techniques and blockchain technology. The BCMPB-RIDMPL technique consists of one input layer, three hidden layers, and one output layer to detect the malware. The input layer receives the number of applications and malware features as input. After that, the malware features are sent to the hidden layer 1, in which feature selection is carried out using point biserial correlation, which reduces the time required to detect the malware. Then, the selected features and applications are sent to the hidden layer 2. In that layer, Miyaguchi–Preneel cryptographic hash-based blockchain is applied to generate the hash value for each selected feature. The generated hash values are stored in the blockchain, after which the classification is performed in the third hidden layer. The BCMPB-RIDMPL technique uses the Ruzicka index to verify the hash values of the training and testing malware features. If the hash is valid, then the application is classified as malware, otherwise it is classified as benign. This method improves the accuracy of malware detection. Experiments have been carried out on factors such as malware detection accuracy, Matthews’s correlation coefficient, and malware detection time with respect to a number of applications. The observed quantitative results show that our proposed BCMPB-RIDMPL method provides superior performance compared with state-of-the-art methods.