Membership Inference Attack is an approach to find out if a particular data point is included in the dataset used to train a target machine learning model. It consists of three steps: (1) build datasets to train 'shadow' models that mimic the behavior of the target model; (2) train such shadow models; (3) train attack models on the training and test sets of the shadow models, using also the membership to a training set as a label. The approach exploits the fact that a ML model usually behaves differently on samples it has already seen, due, for instance, to overfitting.