Using ML and DL Algorithms for Intrusion Detection in the Industrial Internet of Things

In this chapter, we present the methods and metrics used to analyze the best approach to develop an IDS for industrial networks using ML algorithms. Using datasets present in the literature, several experiments are conducted aiming to choose the best approach to develop an efficient IDS for industrial networks. In order to achieve this goal, the performance of the training model using the logistic regression algorithm in three different scenarios is evaluated, considering the learning time duration and other metrics from the confusion matrix, such as accuracy, FAR, UR, MCC, and sensitivity.