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

Federal learning data tamper-proof monitoring method and related device

A monitoring device and anti-tampering technology, applied in the direction of integrated learning, digital data protection, etc., can solve the problems that the server cannot judge the credibility of the data, affect the update effect of the global model, and the federated learning lacks a transmission data monitoring mechanism, etc., to achieve data monitoring good performance effect

Active Publication Date: 2021-07-09
SUN YAT SEN UNIV
View PDF12 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application provides a federated learning data anti-tampering monitoring method and related devices, which are used to solve the lack of a monitoring mechanism for transmission data tampering in existing federated learning, which makes the server unable to judge the credibility of the data and affects the update effect of the global model. question

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
  • Federal learning data tamper-proof monitoring method and related device
  • Federal learning data tamper-proof monitoring method and related device
  • Federal learning data tamper-proof monitoring method and related device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiment of the application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiment of the application. Obviously, the described embodiment is only It is a part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0040] For ease of understanding, see figure 1 , an embodiment of a federated learning data tamper-proof monitoring method provided by this application, including:

[0041] Step 101: Send the training configuration data to the screened target device through the server, so that the target device performs local training according to the training configuration data t...

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 federal learning data tamper-proof monitoring method and a related device, and the method comprises the steps: transmitting training configuration data to target equipment obtained after screening through a server, enabling the target equipment to carry out local training according to the training configuration data, and obtaining a training result; calculating a first hash value of the training result through the target device by adopting a preset hash algorithm, sending the first hash value to the block chain, sending the training result to the server, and enabling the block chain to establish connection with the server and the target device through a preset smart contract; and performing result verification through the server according to the received training result and the first hash value obtained from the block chain, and judging that the training result received by the server is not tampered if the verification is passed. The technical problem that the updating effect of a global model is affected due to the fact that a server cannot judge the credibility of data due to the fact that existing federal learning is lack of a transmission data tampering monitoring mechanism is solved.

Description

technical field [0001] The present application relates to the technical field of federated learning, and in particular to a tamper-proof monitoring method for federated learning data and related devices. Background technique [0002] Blockchain is a shared database and a new application model of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. The data or information stored in the blockchain has the characteristics of "tamper-proof", "traceable", "open and transparent", and "collective maintenance". Based on these characteristics, blockchain technology has laid a solid "trust" foundation and created a reliable "cooperation" mechanism. The smart contract is an end code that is stored on the block and can run in the blockchain. It can be simply understood as an automatically executable script that runs on the blockchain framework without third-party control; therefore, it can be executed accord...

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): G06F21/64G06N20/20
CPCG06F21/64G06N20/20
Inventor 黄华威张可姗郑子彬
Owner SUN YAT SEN UNIV
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