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

Key level-to-level management method and device for federated learning and privacy calculation

A hierarchical management and key technology, applied to the public key and key distribution of secure communication, can solve the problems of key leakage and inability to restore sensitive data, so as to prevent key leakage, reduce costs and deployment time, and protect data Effects on Security and Privacy

Active Publication Date: 2022-05-13
CLUSTAR TECH LO LTD
View PDF9 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in this way, when the device storing the key is restarted due to force majeure interference and the key in the memory is lost, the encrypted sensitive data may not be recovered
By solidifying the key in the application and writing the application to the disk together, although this can use the application in the disk to restore encrypted sensitive data, it introduces the possibility that the application is cracked and the key is leaked. Security risks

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
  • Key level-to-level management method and device for federated learning and privacy calculation
  • Key level-to-level management method and device for federated learning and privacy calculation
  • Key level-to-level management method and device for federated learning and privacy calculation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] In order to solve the above-mentioned key leakage problem and key loss problem caused by server restart, the embodiment of the present application proposes a key hierarchical management method and device for federated learning and privacy computing. Wherein, the key hierarchical management method includes: using the root key management server to generate a first public key-private key pair based on an asymmetric encryption algorithm, and sending the public key of the first public key-private key pair to the A first participant in the execution environment; through the first execution environment of the first participant, use the public key of the first public key-private key pair to encrypt the confidential information to obtain an encryption result of the confidential information, and convert the confidential information to at least a portion of the encrypted result of the information is stored in a second execution environment different from the first execution environ...

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 relates to a secret key level-to-level management method and device for federated learning and privacy calculation. In various applications in the technical fields of federated learning and privacy computing, the method and the device prevent the secret key from being leaked and overcome the problem of secret key loss caused by factors such as restart, meanwhile, various feasible external resources can be utilized, data security and privacy information can be protected, cost is reduced, and deployment time is shortened.

Description

technical field [0001] The present application relates to the technical field of data security and privacy protection, in particular to the technical field of federated learning and privacy computing, and in particular to a key hierarchical management method and device for federated learning and privacy computing. Background technique [0002] With the increasing emphasis on data security and personal information privacy, privacy computing technology and federated learning technology have achieved tremendous development. Privacy computing refers to data-related calculations, analysis, and mining of data value under the premise of protecting privacy information security. Federated learning refers to the joint training of encrypted data by all participants who own data without sharing data resources and the data does not go out of the local area, so as to jointly optimize the shared machine learning model and achieve win-win cooperation. In the application scenario of federat...

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): H04L9/30H04L9/08H04L9/40
CPCH04L9/3006H04L9/0897H04L9/083H04L63/0442
Inventor 张翔宇张春海孙军欢
Owner CLUSTAR TECH LO LTD
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