System and method for protecting information
AssigneeMicrosoft Technology Licensing, LLC
InventorsUwe Helmut Jost, Patrick A. Naylor, Dushyant Sharma, Ljubomir Milanovic, William F. Ganong, III
Life of this patent
Estimating the term…
Abstract
A method, computer program product, and computing system for receiving input content that may include sensitive information for processing by a machine learning model; processing the input content with the machine learning model to generate output content; processing the output content to determine if the output content includes any sensitive information; and if the output content includes any sensitive information, scrutinizing the input content to determine if the input content supports the inclusion of the sensitive information in the output content.
Claims20
A computer-implemented method, executed on a computing device, comprising:
- receiving, from a user, input content for processing by a machine learning model;
- processing, by the machine learning model, the input content to generate output content, the output content including sensitive information excluded from the input content that is not publicly available;
- processing the output content to remove the sensitive information from the output content responsive to determining that the sensitive information in the output content is both excluded from the input content and not publicly available;
- and
- providing the processed output content to the user in response to the input content.
A computer program product residing on a non-transitory computer readable medium having a plurality of instructions stored thereon which, when executed by a processor, cause the processor to perform operations comprising:
- receiving, from a user, input content for processing by a machine learning model;
- processing, by the machine learning model, the input content to generate output content, the output content including sensitive information excluded from the input content that is not publicly available;
- processing the output content to remove the sensitive information from the output content responsive to determining that the sensitive information in the output content is both excluded from the input content and not publicly available;
- and
- providing the processed output content to the user in response to the input content.
A computer-implemented method, executed on a computing device, comprising:
- receiving, from a user, input content for processing by a machine learning model;
- processing, by the machine learning model, the input content to generate output content, the output content including sensitive information excluded from the input content that is not publicly available;
- processing the output content to remove the sensitive information from the output content responsive to determining both that the input content lacks support for inclusion of the sensitive information in the output content and that the sensitive information is not publicly available;
- and
- providing the processed output content to the user in response to the input content.
Dependencies are inferred from the claim text.