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

Federated learning training data privacy enhancement method and system

A technology of learning and training and privacy, applied in the direction of digital transmission system, transmission system, electrical components, etc., to achieve the effect of increasing flexibility and scalability, ensuring security, and ensuring safety

Active Publication Date: 2019-12-13
UNIV OF JINAN
View PDF5 Cites 95 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

So, purely adding noise is flawed

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
  • Federated learning training data privacy enhancement method and system
  • Federated learning training data privacy enhancement method and system
  • Federated learning training data privacy enhancement method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] A method for enhancing the privacy of federated learning training data, applied to: n clients that do not trust each other, denoted as F i (i=1...n), and two semi-honest third-party servers, respectively denoted as the first server S and the second server S'. Among them, the server S' is configured to: be responsible for the communication between the client and the server S and the calculation inside S'; be responsible for storing the data uploaded by the client and various data in the calculation process; and store the public parameters sent by the server S PP. The server S is configured to: only interact with the server S'; be responsible for storing the data sent by the server S' and various data of the calculation process; be responsible for storing the public parameters and master keys generated by the BCP algorithm.

[0057] Such as Figure 1-2 As shown, the method specifically includes the following steps:

[0058] Step 1: Server S uses BCP algorithm to genera...

Embodiment 2

[0087] The purpose of this embodiment is to provide a system for enhancing the privacy of federated learning training data.

[0088] In order to achieve the above purpose, this embodiment provides a federated learning training data privacy enhancement system, including a first server, a second server and multiple clients participating in federated learning.

[0089] The first server generates public parameters and a master key, and sends the public parameters to the second server; if the encrypted model parameters and the corresponding public key are received, decrypt each blinded encrypted model parameter based on the master key, and pass weighted average to obtain the global model parameters, respectively adopting the public key of each client to encrypt the global model parameters, and sending to the second server;

[0090] The second server receives and stores public parameters; receives encrypted model parameters and corresponding public keys, and sends them to the first ...

Embodiment 3

[0093] The purpose of this embodiment is to provide a server.

[0094] The server is applied to federated learning, communicates with multiple clients participating in federated learning via another server, and is configured to:

[0095] Generate a public parameter and a master key, and send the public parameter to another server for downloading by multiple clients; wherein the public parameter is used for each client to generate its own public key;

[0096] Receiving encrypted model parameters and corresponding public keys from another server, wherein the encrypted model parameters are obtained by encrypting the local model parameters obtained by each client based on their respective public keys;

[0097] The encrypted model parameters are decrypted based on the master key, the global model parameters are obtained by weighted average, the global model parameters are encrypted with the public key of each client, and sent to each client through another server.

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

The invention discloses a federated learning training data privacy enhancement method and system, and the method comprises the steps that a first server generates a public parameter and a main secretkey, and transmits the public parameter to a second server; a plurality of clients participating in federated learning generate respective public key and private key pairs based on the public parameters; the federated learning process is as follows: each client encrypts a model parameter obtained by local training by using a respective public key, and sends the encrypted model parameter and the corresponding public key to a first server through a second server; the first server carries out decryption based on the master key, obtains global model parameters through weighted average, carries outencryption by using a public key of each client, and sends the global model parameters to each client through the second server; and the clients carry out decrypting based on the respective private keys to obtain global model parameters, and the local models are improved, and the process is repeated until the local models of the clients converge. According to the method, a dual-server mode is combined with multi-key homomorphic encryption, so that the security of data and model parameters is ensured.

Description

technical field [0001] The invention belongs to the technical field of data security protection, and in particular relates to a method and system for enhancing the privacy of federated learning training data. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] In recent years, with the rapid development of machine learning technology and technology, the good experience of mobile devices has continuously improved people's living standards. However, traditional machine learning applications require the client to upload the user's data to the server and train the model on the server, which may lead to serious leakage of user privacy. For example, in the 2016 data breach incident of Uber in the United States, the 2017 Qudian student information breach incident and the 2018 Facebook user information breach incident, the servers of these three co...

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): H04L9/00H04L29/06
CPCH04L63/0428H04L9/008H04L63/1408H04L63/1441
Inventor 赵川张谦荆山陈贞翔张波王吉伟
Owner UNIV OF JINAN
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com