Private transfer learning

Abstract

Embodiments of a method for private transfer learning are disclosed. The method includes generating a machine learning model including a training application programming interface (API) and an inference API. The method further includes encrypting the machine learning model using a predetermined encryption mechanism. The method also includes copying the encrypted machine learning model to a trusted execution environment. The method also includes executing the machine learning model in the trusted execution environment using the inference API.

Description

technical field [0001] The present disclosure relates to private transfer learning, and more particularly, to secure portable DNNs for private transfer learning. Background technique [0002] Deep Neural Networks (DNNs) are machine learning architectures. A machine learning architecture is a computer system, such as a machine, that can learn. One of the things that machines can learn is how to classify objects, for example, how to distinguish images of people from images of objects. Thus, a DNN can take an image as input, and output a label for that image, which indicates whether the DNN classifies the image as a person or an object. The act of classifying an object through machine learning such as a DNN model is referred to herein as inference or forward transfer. In contrast, the backward pass involves training a DNN model, which is a computer program that learns to perform predetermined classifications. Training a DNN model to be accurate can be complex, and thus reli...

AI Technical Summary

Problems solved by technology

Training a DNN model to be accurate can be complex, and thus relies on relatively large amounts of data to learn how to perform common tasks, such as distinguishing images of people from images of objects

Images