Supercharge Your Innovation With Domain-Expert AI Agents!

Neural network model encryption protection system and method related to data random encryption

A neural network model and random encryption technology, applied in the field of artificial neural network protection mechanism to achieve the effect of rights protection

Active Publication Date: 2018-11-16
CHENGDU PANOAI INTELLIGENT TECH CO LTD
View PDF5 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the above defects of the existing artificial neural network protection mechanism, the present invention provides a neural network model encryption protection system and method involving random encryption of data

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
  • Neural network model encryption protection system and method related to data random encryption
  • Neural network model encryption protection system and method related to data random encryption
  • Neural network model encryption protection system and method related to data random encryption

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] A system structure diagram of a neural network model encryption protection system 100 involving random encryption of data is shown in the appendix of the specification. figure 1 , for the encryption principle of the encryption module 2 of the encryption protection system 100, please refer to the appendix of the description. figure 2 , the encryption protection system 100 includes a data input module 1 , an encryption module 2 , an encrypted data input module 3 , an artificial neural network model module 4 and a data output module 5 . The data input module 1 is connected with the signal of the encryption module 2, the encryption module 2 is connected with the signal of the encrypted data input module 3, the encrypted data input module 3 is connected with the signal of the artificial neural network model module 4, and the artificial neural network model module 4 is connected with the signal of the data output module 5. connected.

[0048] Further, the data input module ...

Embodiment 2

[0060] A neural network model encryption protection method involving random encryption of data proposed by the present invention includes the following steps:

[0061] A. Provide original input data D;

[0062] S. Encrypt the original input data D to generate encrypted input data D ’ ;

[0063] B. Encrypt the input data D ’ Input to the artificial neural network model, the artificial neural network model encrypts the input data D ’ perform calculations and get results;

[0064] C. Output the calculated results.

[0065] Wherein, step S specifically includes:

[0066] S1. provide a group of keys S with N digits as a control amount, the key S specifically defines the encryption process for the original input data D; wherein, the length of the key S is determined by the encryption method in the encryption process and the encryption requirements. Defined; each of the N-digit numbers of the key S is selected from one of the Arabic numerals 0-9;

[0067] S2. Convert the origi...

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 belongs to the field of artificial neural network protection mechanisms, in particular to a neural network model encryption protection system and method related to data random encryption. The system comprises an encryption module; a data division module in the encryption module converts the original input data into a two-dimensional structure, which is divided into a plurality of to-be-processed subblocks; a password generation module generates the same passwords as the subblock structures, respectively; a password embedding module is used for embedding the passwords into the corresponding subblocks in a superposed manner; a data reconstruction module reconstructs each subblock embedded with the passwords into a two-dimensional structure according to the previous subblock division manner, and encrypted input data is generated. Compared with the prior art, the neural network model encryption protection system and method related to data random encryption in the invention embed a protective password into the artificial neural network model in the case that the calculated quantity is not significant in increase and the performances of the artificial neural network are maintained so that any duplication, secondary development or modification does not affect the protective password after the artificial neural network model is released.

Description

technical field [0001] The invention belongs to the field of artificial neural network protection mechanisms, in particular to a neural network model encryption protection system and method involving random encryption of data. Background technique [0002] Deep learning is the main technical solution for current artificial intelligence applications. The artificial neural network model trained with deep learning technology is the labor result of the wisdom of the initial developers. However, in the process of publishing and applying the artificial neural network model, its network structure and node weights will be completely exposed to the outside world. After the artificial neural network model is released and / or applied by a third party, it is easy to be copied, redeveloped or modified, resulting in damage to the rights and interests of the original developers. The protection schemes suitable for artificial neural network models in the prior art mainly include overall ne...

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): G06F21/60G06N3/08H04L9/08
CPCG06F21/602G06N3/08H04L9/0869
Inventor 尹愚
Owner CHENGDU PANOAI INTELLIGENT TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com