Bank of America Corporation

Laura Stillman Lavender

Edward Lee Traywick

Christopher D Nobile

Nicholas O'reilly

Joshua R Johnson

Arrangements for machine learning-based anomaly detection are provided. In some examples, historical data related to user interactions with enterprise organization resources and location may be received and used to train a machine learning model. Current user interaction data, as well as current location data, may be received. The current user interaction data and location data may be input to the machine learning model and the model may be executed to detect any anomalies in the data. If no anomalies are detected, the process may return to receive subsequent user interaction and location data for analysis. If an anomaly is detected, a notification may be generated and transmitted to an administrator computing device for display by the device.

Machine learning-based anomaly detection

Arrangements for controlling access to secure resources when a VPN is detected. In some examples, a request to access an enterprise organization resource may be received by a computing platform and from a user computing device. The computing platform may determine whether a VPN is detected in the request. If not, the computing platform may enable a connection between the user computing device and the requested resource. If a VPN is detected, data may be extracted from the request. The data may include identification of a user, a type of VPN and/or a type of user computing device. The extracted data may be input to an AI/ML model and the model may be executed to generate a customized notification. The notification may indicate that use of a VPN has been detected and may provide customized instructions to disable the type of VPN detected.

Controlling access to secure systems based on virtual private network detection

Arrangements for detecting an email deluge are provided. A computing platform may train an artificial intelligence (AI) engine. The computing platform may receive a group of electronic messages. The computing platform may identify a user profile based on an electronic user identifier associated with the group of electronic messages. The computing platform may determine one or more electronic characteristics based on content associated with the group of electronic messages. The computing platform may generate one or more rules to determine whether a deluge has been detected. Based on determine that a deluge has been detected, the computing platform may quarantine the group of electronic messages and/or perform other actions.

Growing community of inventors

Washington, DC, United States of America

Laura Stillman Lavender