Intel Corporation

Ria Cheruvu

Anahit Tarkhanyan

Ned M Smith

Francesc Guim Bernat

Kshitij Arun Doshi

Sunil K Cheruvu

Embodiments are directed to immutable watermarking for authenticating and verifying artificial intelligence (AI)-generated output. An embodiment of a system includes a processor of a monitoring system, wherein the processor is to: receive first content from a first device and second content from a second device, wherein the first content comprises output of inferences of a machine learning (ML) model as applied to captured content at the first device; extracting, from a digital signature corresponding to the first content, a global unique identifier (GUID) of the ML model that generated the first content; verify the extracted GUID against data obtained from a shared registry, the data comprising identifying information of the ML model including the GUID; in response to successfully verifying the extracted GUID, provide the first content for consumption at an application and indicate that the content is generated by the ML model having verified authenticity.

Immutable watermarking for authenticating and verifying AI-generated output

Methods, apparatus, systems, and articles of manufacture to protect proprietary functionality and/or other content in hardware and software are disclosed. An example computer apparatus includes; a first circuit including a first interface, the first circuit associated with a first domain; a second circuit including a second interface, the second circuit associated with a second domain; and a chip manager to generate a first authenticated interface for the first interface using a first token and to generate a second authenticated interface for the second interface using a second token to enable communication between the first authenticated interface and the second authenticated interface.

Apparatus, systems, and methods to protect hardware and software

Embodiments are directed to immutable watermarking for authenticating and verifying artificial intelligence (AI)-generated output. An embodiment of a system includes a processor of a monitoring system, wherein the processor is to: receive first content from an edge device and second content from an adversary system, wherein the first content comprises output of a machine learning (ML) model as applied to captured content at the edge device; receive a digital signature corresponding to the first content; process the digital signature to extract a global unique identifier (GUID) of the ML model that generated the first content; verify the extracted GUID against data obtained from a shared registry; in response to successfully verifying the extracted GUID, provide the first content for consumption at a monitoring consumption application; and in response to determining that the second content is not associated with a verifiable GUID, refuse the second content at the monitoring consumption application.

Embodiments are directed to immutable watermarking for authenticating and verifying artificial intelligence (AI)-generated output. An embodiment of a system includes a hardware accelerator to perform processing related to a machine learning (ML) model and one or more processors including a hash generator. In one implementation, the hash generator is to identify a global unique identifier (GUID) for the ML model, generate a digital signature for content generated by an inference stage of the ML model, the digital signature based on at least the GUID of the ML model and the content generated by the ML model, and transmit the content and the digital signature to a content consumer platform.

Growing community of inventors

Tempe, AZ, United States of America

Ria Cheruvu