US Patent 11341277 Method and system for securing machine learning models
Patent 11341277 was granted and assigned to NEC on May, 2022 by the United States Patent and Trademark Office.
All edits
US Patent 11341277 Method and system for securing machine learning models
A system for machine learning that is configured to receive an input having a plurality of features and predict one or more attributes of the input. The system includes a security mechanism, which determines an initial value for each of the features; determines a perturbation value for each of the features, the perturbation being randomly selected; adds the perturbation value to the initial value to determine a perturbed value for each of the features; and quantizes the perturbation value for each of the features to determine a quantized value for each of the features. The system also includes a classifier that receives the quantized value for each of the features and predict the one or more attributes of the input based on the quantized value for each of the features.
Find more entities like US Patent 11341277 Method and system for securing machine learning models
