Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Privacy-preserving machine learning

A machine learning and privacy protection technology, applied in the fields of digital data protection, neural learning methods, instruments, etc., can solve problems such as data that cannot be used for inference

Inactive Publication Date: 2019-12-03
VISA INT SERVICE ASSOC
View PDF0 Cites 58 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this setup, the server has full access to the plaintext data, but wants to ensure that the published model cannot be used to infer the data used during training

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 approach

[0289] The system is implemented in C++. In all our experiments, the domain size was set to 2 64 . Thus, we observe that modulo arithmetic can be implemented in C++ using regular arithmetic on unsigned long integer types at no additional cost. This is significantly faster than any number theory library capable of handling operations in arbitrary domains. For example, we test that integer addition (multiplication) is 100× faster than modular addition (multiplication) in the same domain implemented in the GMP [5] or NTL [7] libraries. More generally, the finite field Any element in can be represented by one or several unsigned long integers, and addition (multiplication) can be calculated by one or several regular additions (multiplications) plus some bit operations. The speedup of such implementations is similar to using general number theory libraries. We use the Eigen library [2] to handle matrix operations. OT and obfuscation circuits are implemented using the EMP...

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

New and efficient protocols are provided for privacy-preserving machine learning training (e.g., for linear regression, logistic regression and neural network using the stochastic gradient descent method). A protocols can use the two-server model, where data owners distribute their private data among two non-colluding servers, which train various models on the joint data using secure two-party computation (2PC). New techniques support secure arithmetic operations on shared decimal numbers, and propose MPC-friendly alternatives to non-linear functions, such as sigmoid and softmax.

Description

Background technique [0001] Machine learning techniques are widely used in practice to generate predictive models for medicine, finance, recommendation services, threat analysis, and authentication techniques. Huge amounts of data collected over time enable new solutions to old problems, and advances in deep learning have enabled breakthroughs in language, image, and text recognition. [0002] Large Internet companies collect users' online activities in order to train recommender systems that predict their future interests. Health data from various hospitals and government organizations can be used to generate new diagnostic models, while financial companies and payment networks can combine transaction history, merchant data, and account holder information to train more accurate fraud detection engines. [0003] figure 1 A high-level diagram depicting a process 100 for training and using a machine learning model is shown. Process 100 begins with training data, shown as exis...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08G06F21/62
CPCG06F21/6254G06N3/084H04L9/008H04L2209/46G06N3/048G06N3/045G06F21/6245G06N3/08H04L9/085
Inventor P·莫哈塞尔Y·张
Owner VISA INT SERVICE ASSOC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products