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

Federal learning privacy reasoning attack-oriented defense method based on parameter compression

A parameter and privacy technology, applied in the field of network security, can solve problems such as the decline of the accuracy rate of the global model, and achieve the effect of ensuring accuracy, reducing parameter information, and defending private data information.

Pending Publication Date: 2022-03-25
HANGZHOU HIKVISION DIGITAL TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in order to effectively protect private data, as the noise increases, the accuracy of the global model decreases

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 privacy reasoning attack-oriented defense method based on parameter compression
  • Federal learning privacy reasoning attack-oriented defense method based on parameter compression
  • Federal learning privacy reasoning attack-oriented defense method based on parameter compression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present application as recited in the appended claims.

[0022] The terminology used in this application is for the purpose of describing particular embodiments only, and is not intended to limit the application. As used in this application and the appended claims, the singular forms "a", "the", and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise.

[0023] In order to enable those skilled ...

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 provides a federated learning privacy inference attack-oriented defense method based on parameter compression, and the method comprises the steps: determining a target parameter in local model parameters of a target client according to the difference of the local model parameters of the target client before and after training, so as to defend the privacy inference attack; determining compression model parameters of the target client; and determining global model parameters according to the compression model parameters of the target client. According to the method, the local private data features of the client can be protected under the condition of ensuring the accuracy of the global model, and the defense against the privacy reasoning attack is realized.

Description

technical field [0001] The present application relates to the technical field of network security, in particular to a defense method based on parameter compression for federated learning privacy reasoning attacks. Background technique [0002] Federated Learning (Federated Learning) is a machine learning framework that implements private data and shared models. Each participant client (referred to as the client) has private data, and multiple clients jointly train a model. For each round of training, each client uploads the model parameters obtained by its local training (which can be called local model parameters), and the central server performs federated averaging to obtain global model parameters, and then sends them to each client for the next round of training . [0003] With the popularity of federated learning, the attack methods against federated learning are also increasing. The client uses Generative adversarial network (GAN) to conduct privacy reasoning attacks...

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): G06F21/62G06N20/00
CPCG06F21/6245G06N20/00
Inventor 王滨王星张峰王伟钱亚冠
Owner HANGZHOU HIKVISION DIGITAL TECH
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