Homomorphic encryption method and application thereof in privacy protection classifier

A homomorphic encryption and encryption system technology, applied in digital data protection, instruments, machine learning, etc., can solve problems such as excessive calculation overhead, inability to batch multiplication or addition, and Bayesian risk is not small enough to reduce errors. Effects of classification loss, reduced interaction rounds, and reduced Bayesian risk

Pending Publication Date: 2022-04-08
GUANGZHOU UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, for multiply-add (M-A) type classifiers, the partial homomorphic encryption PHE method is not applicable, while the fully homomorphic encryption FHE method has poor performance in large ciphertext expansion, excessive computational overhead, and limited

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
  • Homomorphic encryption method and application thereof in privacy protection classifier
  • Homomorphic encryption method and application thereof in privacy protection classifier
  • Homomorphic encryption method and application thereof in privacy protection classifier

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0042] Such as figure 1 As shown, the homomorphic encryption method of the present embodiment is to construct a homomorphic encryption tool on the basis of the Paillier encryption system:

[0043] MASE = (KeyGen, Enc, Dec-int, Dec, Mul, Add),

[0044] Specific steps are as follows:

[0045] S1. Both the sender and receiver of the message use the KeyGen algorithm to generate the public key pk and private key sk;

[0046] KeyGen is the security parameter κ∈N used in the Paillier encryption system and returns the probability algorithm of the public key / private key pair (pk, sk), recorded as: (pk, sk)←KeyGen(1 κ ), and pk=(n,g), sk=(λ,μ);

[0047] Among them, n=p*q, p and q are two different large prime numbers randomly selected; λ=lcm(p-1,q-1), lcm(·,·) is expressed as finding the least common multiple of two parameters ; g is a random number, satisfying means less than n 2 and with n 2 The set of coprime modulo n 2 A group of multiplication, m represents the integer for...

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 homomorphic encryption method and application of the homomorphic encryption method to a privacy protection classifier. The method comprises the following specific steps: generating a public key pk and a private key sk by using a key generation algorithm KeyGen, encrypting a plaintext Q, and decrypting a ciphertext c. Compared with the prior art, the method has the advantages that the defect that multiplication can be carried out only when digits in a fixed-point representation system are represented as shared integers is overcome, a good balance effect is achieved between calculation efficiency and communication interaction, expected misclassification loss is reduced when the method is applied to privacy protection classifier encryption, and the privacy protection classifier encryption efficiency is improved. And the same accuracy rate as that of the original Bayesian classifier with the minimum Bayesian risk is kept.

Description

technical field [0001] The invention belongs to the technical field of data encryption algorithms, and in particular relates to a homomorphic encryption method and its application on a privacy protection classifier. Background technique [0002] In the field of machine learning, classifiers belong to the key core. With the increasing complexity of data nature, data volume, data calculation, classification and data mining requirements, how to ensure data privacy in the classification process is particularly important. The encryption used to protect privacy needs to focus on the training phase and the prediction phase. [0003] When protecting the privacy of the prediction stage in the existing technology, different cryptographic tools are used for protection according to the complexity of classifiers; for simpler classifiers, partial homomorphic encryption PHE tools are used to achieve privacy protection; for more complex Classifiers often use fully homomorphic encryption, F...

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): G06F21/60G06F21/64G06K9/62G06N20/00
Inventor 高崇志陈文彬李保珲何锫
Owner GUANGZHOU UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products