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

Handwriting recognition method based on encrypted neural network

A neural network and handwriting recognition technology, applied in the intersection of information security and artificial intelligence, can solve problems such as data processing that cannot be encrypted

Active Publication Date: 2019-11-22
NANJING UNIV OF POSTS & TELECOMM
View PDF4 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing machine learning technology cannot process the encrypted data, but the homomorphic encryption algorithm can directly perform specific four arithmetic operations on the ciphertext results. The result of the operation is the same

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
  • Handwriting recognition method based on encrypted neural network
  • Handwriting recognition method based on encrypted neural network
  • Handwriting recognition method based on encrypted neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0090] Such as figure 2 A kind of handwriting recognition method based on encryption neural network shown, comprises the following steps:

[0091] Step 1: Preprocessing feature data and label data;

[0092] Step 2: Build a deep learning model and train hyperparameters;

[0093] Step 3: Homomorphically encrypt the preprocessed data;

[0094] Step 4: Improve the matrix dot product and activation function to build an encrypted neural network;

[0095] Step 5: Use encrypted neural network for classification recognition.

[0096] The data preprocessing in step 1 specifically includes the following steps.

[0097] A1: Perform z-score standardization processing on feature data;

[0098] Feature data has various value ranges when unprocessed, some features are small floating-point numbers, and some features are relatively large integers;

[0099]

[0100]

[0101]

[0102] Among them, X i Represents characteristic data, m represents the size of characteristic data, E(...

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 handwriting recognition method based on an encrypted neural network. The handwriting recognition method comprises the following steps: 1, preprocessing feature data and labeldata; 2, constructing a deep learning model, and training hyper-parameters; 3, performing homomorphic encryption on the preprocessed data; 4, improving matrix point multiplication and an activation function, and constructing an encrypted neural network; and 5, carrying out classification identification by utilizing an encryption neural network, and combining a homomorphic encryption algorithm witha neural network model to realize protection of data privacy and prevent leakage of data information, so that the method is mainly applied to the field of information security and artificial intelligence crossing.

Description

technical field [0001] The invention relates to an image recognition method, in particular to a handwriting recognition method, belonging to the intersection fields of information security and artificial intelligence. Background technique [0002] Nowadays, machine learning is developing rapidly, and all major research fields are trying to use machine learning technology to practice artificial intelligence. However, when applying machine learning technology to a problem involving medical, financial or other sensitive data, we not only require it to have accurate prediction capabilities, but also to pay attention to the privacy and security of the data. It may be legally and ethically prohibited to use it in these scenarios. [0003] The existing machine learning technology cannot process the encrypted data, but the homomorphic encryption algorithm can directly perform specific four arithmetic operations on the ciphertext results. The result of the operation is the same. I...

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): G06K9/00G06F21/60G06N3/04G06N3/06G06N3/08G06K9/62
CPCG06N3/061G06N3/08G06F21/602G06V30/36G06N3/044G06F18/2411
Inventor 王薇刘永双刘林峰
Owner NANJING UNIV OF POSTS & TELECOMM
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