Verizon Communications Inc.
Systems and methods for utilizing machine learning models to detect cloud-based network access anomalies

Abstract:

A device may receive log data identifying access of user devices to containers provided by a cloud-based network, and may aggregate the log data to generate aggregated log data identifying container profiles associated with the containers. The device may train one or more machine learning models, with the aggregated log data, to generate one or more trained machine learning models, and may receive particular log data identifying access of a particular user device, of the user devices, to a particular container of the containers provided by the cloud-based network. The device may process the particular log data, with the one or more trained machine learning models, to identify an anomaly associated with the access of the particular user device to the particular container, and may perform one or more actions based on identifying the anomaly.