Abstract: A system for controlling access to an electronic resource can comprise a set of sensors and one or more processors. A first sensor in the set of sensors may detect first data indicating a characteristic of a user of the electronic resource. A second sensor in the set of sensors may detect second data indicating a characteristic of an environment of the electronic resource. The processors may use an ensemble of machine learning models to generate a score characterizing the user and characterizing the environment. The generated score may be evaluated based on one or more access criteria. Access to the electronic resource may be controlled based on the evaluation of the score.

Abstract: A system for evaluating trained models comprises one or more processors configured to cause the system to: receive a trained model; receive test data comprising a plurality of data objects; receive baseline classification data assigning each data object to a class; apply one or more perturbation operations to the test data to generate, for each data object, a respective plurality of perturbed data objects; apply the trained model to each perturbed data object to generate post-perturbation classification data, wherein the post-perturbation classification data indicates classification of the respective perturbed data object into at least one class and an associated confidence level of the trained model with respect to the classification; determine, for each perturbed data object, whether the post-perturbation classification data indicates a misclassification as compared to the baseline classification data; and generate and display a visualization based on the determination of whether the post-perturbation class

Abstract: A system for controlling access to an electronic resource can comprise a set of sensors and one or more processors. A first sensor in the set of sensors may detect first data indicating a characteristic of a user of the electronic resource. A second sensor in the set of sensors may detect second data indicating a characteristic of an environment of the electronic resource. The processors may use an ensemble of machine learning models to generate a score characterizing the user and characterizing the environment. The generated score may be evaluated based on one or more access criteria. Access to the electronic resource may be controlled based on the evaluation of the score.