Privacy-preserving machine learning

A machine-learning, protected technique for applications in the field of privacy-preserving machine learning

Active Publication Date: 2019-03-01
MICROSOFT TECH LICENSING LLC
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the user's lack of control over the infrastructure within a

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Privacy-preserving machine learning
  • Privacy-preserving machine learning
  • Privacy-preserving machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The detailed description provided below in connection with the accompanying drawings is intended as a description of the present example and is not intended to represent the only form of making or utilizing the present example. This description sets forth the functions of the examples and the sequence of operations for constructing and operating the examples. However, the same or equivalent functions and sequences can be implemented by different examples.

[0022] Machine learning is increasingly used in a variety of applications such as robotics, medical image analysis, human-computer interaction, livestock management, agriculture, manufacturing, and more. The quality and accuracy of machine learning predictions are usually improved by using a greater amount and variety of training data during the training phase. However, usually training data is difficult and expensive to obtain, and is kept secret.

[0023] In various examples described herein, the privacy preservi...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

A multi-party privacy-preserving machine learning system is described which has a trusted execution environment comprising at least one protected memory region. A code loader at the system loads machine learning code, received from at least one of the parties, into the protected memory region. A data uploader uploads confidential data, received from at least one of the parties, to the protected memory region. The trusted execution environment executes the machine learning code using at least one data-oblivious procedure to process the confidential data and returns the result to at least one ofthe parties, where a data-oblivious procedure is a process where any patterns of memory accesses, patterns of disk accesses and patterns of network accesses are such that the confidential data cannotbe predicted from the patterns.

Description

Background technique [0001] In the case of using third-party cloud computing systems to execute machine learning codes on large amounts of data, there are significant security and privacy concerns. Using third-party computing systems in the cloud provides users with flexibility as they can pay for computing resources when they need them. However, the user's lack of control over the infrastructure within the cloud computing system does lead to security and / or privacy concerns. In particular, users may wish to maintain the confidentiality and integrity of the data processed by the code and the output of machine learning. Currently, however, a malicious system administrator or other malicious observer of a cloud computing system can observe patterns of memory access, disk access, and network access and use these observations to find details about confidential data. [0002] The embodiments described below are not limited to implementations that address any or all disadvantages ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F21/60G06N20/00
CPCG06F21/60G06N20/00G06F21/6245
Inventor M·S·d·S·科斯塔C·A·M·C·福奈特A·梅塔S·诺沃津恩O·奥里蒙科F·舒斯特K·瓦斯瓦尼
Owner MICROSOFT TECH LICENSING LLC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap