US 11,755,771 B2
System, method, and computer-accessible medium for training models on mixed sensitivity datasets
Fardin Abdi Taghi Abad, Champaign, IL (US); Vincent Pham, Champaign, IL (US); Austin Walters, Savoy, IL (US); and Jeremy Goodsitt, Champaign, IL (US)
Assigned to CAPITAL ONE SERVICES, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Jan. 5, 2021, as Appl. No. 17/141,800.
Application 17/141,800 is a continuation of application No. 16/512,581, filed on Jul. 16, 2019, granted, now 10,915,658.
Prior Publication US 2021/0200897 A1, Jul. 1, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 21/62 (2013.01); G06N 20/00 (2019.01)
CPC G06F 21/6245 (2013.01) [G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer hardware arrangement for providing a synthetic dataset related to at least one user of a device, comprising:
a computer hardware arrangement comprising:
a processor; and
a computer-accessible medium having stored thereon computer-executable instructions implementing at least one secure data module, at least one synthetic dataset generating module, and at least one control module,
wherein, when the computer-executable instructions are executed by the processor:
the at least one secure data module stores sensitive data regarding the at least one user;
the at least one synthetic dataset generating module:
periodically updates based on operation of the device by the at least one user, and
generates at least one initial synthetic dataset based on the sensitive data; and
the at least one control module:
receives a request from an application for a dataset related to the at least one user, and
provides the request to the at least one synthetic dataset generating module,
receives a synthetic dataset from the at least one synthetic dataset generating module that is based on the at least one initial synthetic dataset, wherein the synthetic dataset and the sensitive data are indistinguishable to the application during use of the synthetic dataset by the application, and
provides the synthetic dataset to the application.