Fig. 1

Overview of the experimental setup. The samples are spatiotemporal data about location visitation patterns. We simulate reduced data quality and potential protection measures by obfuscating the geographic coordinates (a). The samples are then featurized into vectors encoding temporal visitation patterns and spatial context (b). We simulate a privacy attack on new users by a train-test split (c) and train an XGB model to predict the location category (d). The accuracy is evaluated on the test data (e)