US 11,893,486 B2 · Digital watermarking of machine-learning models

Abstract

In one embodiment, a method includes by a computing device, detecting a sensory input, identifying, using a machine-learning model, one or more attributes associated with the machine-learning model, wherein the attributes are identified based on the sensory input in accordance with the model's training, and presenting the attributes as output. The identifying may be performed at least in part by an inference engine that interacts with the model. The sensory input may include an input image received from a camera, and the model may identify the attributes based on an input object in the input image in accordance with the model's training. The model may include a convolutional neural network trained using training data that associates training sensory input with the attributes. The training sensory input may include a training image of a training object, and the input object may be classified in the same class as the training object.

Claims20

Dependent claims

A device comprising:

a memory;
and
at least one processor configured to:
apply an input to a machine-learning model to identify one or more attributes associated with the machine-learning model, the machine-learning model having been trained to identify the one or more attributes in response to the input, wherein the one or more attributes specify an action associated with the input;
and
perform, independent of the identifying, the action, wherein the action comprises at least one of activating or deactivating one or more features of the machine-learning model, the one or more features being specified by the one or more attributes.

3 more elements

Dependencies are inferred from the claim text.

Digital watermarking of machine-learning models

Life of this patent

Digital watermarking of machine-learning models

Life of this patent

Abstract

Claims20