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

Non-interactive naive Bayesian classification method based on homomorphic encryption

A technology of Bayesian classification and homomorphic encryption, which is applied in the field of information security, can solve the problems of privacy leakage and increased communication costs, and achieve the effects of ensuring security, reducing the risk of privacy leakage, and reducing communication overhead

Pending Publication Date: 2022-02-11
CHONGQING INST OF GREEN & INTELLIGENT TECH CHINESE ACADEMY OF SCI
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Information exchange not only increases the communication cost, but also has the risk of privacy leakage

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
  • Non-interactive naive Bayesian classification method based on homomorphic encryption
  • Non-interactive naive Bayesian classification method based on homomorphic encryption
  • Non-interactive naive Bayesian classification method based on homomorphic encryption

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] Embodiment: In a typical data classification scenario, in order to achieve the purpose of privacy protection, the user encrypts the data he owns and sends the ciphertext to the server; the server substitutes the ciphertext data into the model for classification prediction, and obtains the encrypted data text and send it to the user; the user decrypts the ciphertext to get the classification result.

[0044] In this example, assume that the user "Zhang San" holds a sample data x=(2, 4, 1, 1) to be classified, and the possible classification labels are 1, 2, 3, that is, the data has four characteristics (n= 4), may be classified into three different classifications (s=3), and further assume that each feature takes a value in the set {1, 2, 3, 4, 5} (t=5); suppose the server "Li Four" has model data as prior probability p=(0.317, 0.325, 0.357), and the likelihood matrix is:

[0045]

[0046] Assume that both parties choose BGV as the homomorphic encryption scheme.

[...

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 non-interactive naive Bayesian classification method based on homomorphic encryption, and belongs to the field of information security. The method comprises the following steps: S1, setting security parameters and related encryption and decryption parameters; S2, generating a public and private key pair and an operation key according to the security parameters; S3, encoding the sample data and then encrypting the sample data to generate encrypted data; S4, performing homomorphic classification on the encrypted data by a naive Bayes prediction model; and S5, decrypting by using the private key to obtain a classification result of the sample data. According to the non-interactive naive Bayesian classification method based on homomorphic encryption, no information interaction exists between the user and the server in the calculation process in the classification stage, and the communication overhead and the privacy disclosure risk can be greatly reduced.

Description

technical field [0001] The invention relates to a non-interaction naive Bayesian classification method based on homomorphic encryption, and belongs to the field of information security. Background technique [0002] Data classification is one of the fundamental goals of machine learning and a fundamental building block of more complex artificial intelligence systems. The Naive Bayesian classifier is a simple but powerful classifier that can be used for spam identification, medical report analysis, product recommendation, etc. Common application frameworks such as figure 1 As shown, the user submits the data to the server, and the server classifies the data according to the existing model and sends the classification result to the user. With the increasing demand for data privacy protection, in fact, figure 1 The data in the middle gray box has privacy protection requirements: the server does not want to disclose model information, and the user does not want to disclose sa...

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): G06K9/62G06F21/60
CPCG06F21/602G06F18/24155
Inventor 陈经纬杨文强吴文渊冯勇
Owner CHONGQING INST OF GREEN & INTELLIGENT TECH CHINESE ACADEMY OF SCI
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