Bank of America Corporation

Scott Fennell

Jeffrey Wayne Texada

Jennie Kathleen Egbert

A method for classifying a suspicious text message on a user device is disclosed. The method includes communicating between a classification processor and a user device, where the classification processor receives the suspicious text message from the user device, the suspicious text message having information data. The method includes applying a hashing function to the information data to generate hashed information data. The method includes storing the hashed information data in one or more of a plurality of network nodes in a blockchain network, and comparing the hashed information data to known hashed malicious data stored on a database. The method includes classifying the information data as containing malicious data based on the comparison.

System and method for classifying suspicious text messages received by a user device

Arrangements for providing typosquatting detection and notification functions are provided. In some aspects, user input data may be received. The user input may include a website or website address received via a web browser address bar displayed on a user computing device. The user input may be analyzed, using a machine learning model, to determine a likelihood of typosquatting. The determined likelihood may be compared to a threshold and, if the likelihood is below the threshold, the user may proceed with the request to access the website. If the likelihood meets or exceeds the threshold, a notification or user interface may be generated requesting user input confirming that the user input reflects a correct or desired website. User response data may be received and used to update and/or validate the machine learning model.

Growing community of inventors

Carrollton, TX, United States of America

Scott Fennell