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

Method and device for training model

A training model and model technology, applied in the field of training models, can solve problems such as increasing the difficulty of attackers' reverse attacks

Active Publication Date: 2021-09-10
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Second, the prediction results of the model are approximated, which increases the difficulty for attackers to carry out model reverse attacks based on the prediction results

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
  • Method and device for training model
  • Method and device for training model
  • Method and device for training model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain related inventions, rather than to limit the invention. It should also be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

[0033] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and embodiments.

[0034] figure 1 An exemplary system architecture 100 is shown to which embodiments of the method for training a model or the apparatus for training a model of the present application can be applied.

[0035] like figure 1 As shown, the system architecture 100 may include a...

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 embodiment of the invention discloses a method and device for training a model. A specific embodiment of the method comprises the following steps: collecting a user data set; initializing a to-be-trained model; training the to-be-trained model by using the user data set to obtain an original model parameter gradient calculated based on user data in the user data set; performing differential privacy processing on an original model parameter gradient obtained by calculation based on the user data in the user data set to obtain a processing model parameter gradient obtained by calculation based on the user data in the user data set; and updating model parameters of the to-be-trained model by using a processing model parameter gradient obtained by calculation based on user data in the user data set to obtain a trained model. The embodiment provides a method capable of resisting reverse attack of the model, and privacy of user data is effectively protected.

Description

technical field [0001] The embodiments of the present application relate to the field of computer technologies, and in particular to methods and devices for training models. Background technique [0002] At present, machine learning technology has been widely used in many industries. For example, in many fields such as finance, medical care, transportation, and network security, well-trained machine learning models are playing an increasingly important and revolutionary role. Large-scale data is the raw material for training machine learning models. However, while providing services, models trained using a large amount of user data also face various threats and attacks. Model reverse attack is one of the typical attacks. Model reverse attack can launch an attack while using the model service normally, and extract the information of the training set data from the model prediction results, so as to obtain the sensitive characteristics of the user data, resulting in privacy l...

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): G06N20/00G06F21/62
CPCG06N20/00G06F21/6245
Inventor 徐坤蒋精华洪爵
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO 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

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