With the rapid development of the Industrial Internet of Things (IIoT), the need for rapid response, detection and prevention of intrusions into the industrial network has arisen. IIoT networks have special functions and face unique challenges in defending against cyberattacks. These problems are especially urgent as the growth of user demand for IIoT is predicted. The article deals with the security issues of the industrial Internet of things. At the moment, there are some methods of ensuring information security in IIoT networks, which were analyzed in the article. The advantages and disadvantages of existing systems have also been described. Typical attack scenarios in industrial Internet of Things networks were proposed. Based on this analysis, a combined threat detection model using expert systems and such machine learning algorithms as a decision tree, a naive Bayesian classifier, and the k-nearest neighbors method is proposed.