US Patent Application 17927854. SECURE EXECUTION OF A MACHINE LEARNING NETWORK simplified abstract
Contents
SECURE EXECUTION OF A MACHINE LEARNING NETWORK
Organization Name
Microsoft Technology Licensing, LLC
Inventor(s)
SECURE EXECUTION OF A MACHINE LEARNING NETWORK - A simplified explanation of the abstract
- This abstract for appeared for US patent application number 17927854 Titled 'SECURE EXECUTION OF A MACHINE LEARNING NETWORK'
Simplified Explanation
This abstract describes a solution for securely executing a machine learning network. It involves using a trusted execution environment (TEE) and a secure hardware component called uTEE. The first layer of the network is executed in the uTEE using modified parameter values and input data, resulting in an intermediate output. This intermediate output is then further modified in the TEE using secret data and the input, resulting in a corrected intermediate output. Finally, the network output is determined based on this corrected intermediate output. This approach helps protect the confidentiality of the machine learning network.
Original Abstract Submitted
According to implementations of the subject matter described herein, there is provided a solution for secure execution of a machine learning network. An operation of a first network layer of a machine learning network is executed in an uTEE of a computing device based on an input of the first network layer and a first set of modified parameter values, to obtain a first error intermediate In output. The modified parameter values are determined by modifying at least one subset of parameter values of the first network layer with first secret data. A first corrected intermediate output is determined in a TEE of the computing device by modifying the first error intermediate output at least based on the input and first secret data. A network output is determined based on the first corrected intermediate output. In this way, it is possible to protect the confidentiality of the machine learning network.
