With the advent of massive IoT in which objects and humans form highly dense interconnections, the development of new technologies and platforms has been significantly accelerated. In addition, networks and sensing technologies are being blended in various contexts, such as smart factories, digital health, and smart grids, etc. This hyper-connectivity of the blended environment has caused the diversification of the IoT environment and architecture and led to attack surface. Accordingly, the complexity of analyzing and responding to the security breaches is increasing. Hence, recent research has been focused on responding to the potential attack routes using a knowledge graph, a concept that is used to analyze the correlations between the threat data and potentially attackable asset data. However, as the analysis utilizes a single dataset, it has limitation in analyzing and predicting complex threat information. Therefore, to predict and respond to the potential complex security risks on IoBE, a knowledge graph embedding model applicable to blended threats is analyzed in this study.