Access control in smart contracts using machine learning for IoT

One of the challenges we encounter with the growth of the blockchain network is the Access control in the blockchain network. In the blockchain network, the set of financial activities of users that require a digital signature is performed, this information is stored in the blockchain server. Manually, digitally signing and verifying the authenticity of transactions are a time consuming and not a user-friendly process, which is one of the reasons why blockchain technology is not completely accepted. In this paper, an innovative method is proposed based on a combination of clustering and classification methods. First, labeling of data is done using the clustering method and then the labeled data is used to teach the SVM algorithm to determine safe transactions. The proposed method is a relied method on machine learning for access control that automatically signs blockchain transactions and detects abnormal transactions. In order to evaluate the proposed method, testing and analyzing  have been done on ethereum data and with the help of K-Means clustering algorithm and machine vector support method, safe transactions are identified from suspicious ones, in which this method shows the ability to identify with 89 percent of accuracy.