Neural network active protection method and system, storage medium and computing device

An active protection, neural network technology, applied in biological neural network models, computing, neural architecture, etc., can solve the problems of model security threats, lack of active neural network protection methods, illegal copying, redistribution of abuse models, etc. protective effect

Active Publication Date: 2022-06-21
NANJING UNIV OF INFORMATION SCI & TECH +1
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The protection of neural networks has become an increasingly important issue. In order to obtain high-performance models, malicious users may illegally copy, redistribute, abuse models, or use models to provide predictions without permission, which poses a huge threat to model security.
The traditional protection method is a passive verification method after a copyright dispute occurs, and there is currently a lack of neural network active protection methods

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 active protection method and system, storage medium and computing device
  • Neural network active protection method and system, storage medium and computing device
  • Neural network active protection method and system, storage medium and computing device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The above method can enable authorized users to use correct neural network functions more efficiently, while unauthorized users cannot correctly use neural network functions. It effectively solves the traditional method that can only be passively verified after a copyright dispute occurs, and actively protects the security of the neural network more quickly and efficiently.

[0032] Based on the same technical solution, the present invention also discloses the software system of the above method, a neural network active protection system, comprising:

[0033] Result module: if the comparison results are consistent, input correct calculation data to the preset network model layer; if the comparison results are inconsistent, input wrong calculation data to the preset network model layer.

[0034] The data processing flow and method of each module of the above software system are consistent, and will not be repeated here.

[0035] Based on the same technical solution, the...

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 neural network active protection method and system, a storage medium and computing equipment, and the method comprises the steps: extracting a first comparison watermark and a second comparison watermark which are matched with the number of layers from watermarks distributed to a network model and a user before the layer operation of the network model, and comparing the first comparison watermark with the second comparison watermark, and correct or wrong operation data is input according to a comparison result, so that active protection of the neural network is realized.

Description

technical field [0001] The invention relates to a neural network active protection method, system, storage medium and computing equipment, belonging to the field of computer science and technology. Background technique [0002] With the rapid development of artificial intelligence, neural network-based technology is applied to various products, such as face recognition, target tracking, intelligent classification, etc. The protection of neural networks has become an increasingly important issue. In order to obtain high-performance models, malicious users may illegally copy, redistribute, abuse models, or use models to provide predictions without permission, which poses a huge threat to model security. The traditional protection method is a passive verification method after a copyright dispute occurs, and there is currently a lack of neural network active protection methods. Contents of the invention [0003] The invention provides a neural network active protection method...

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): G06F21/16G06F21/12G06N3/04
CPCG06F21/16G06F21/121G06N3/045G06F21/1063
Inventor 陈先意孟宇航刘宇颜凯何俊杰张广星
Owner NANJING UNIV OF INFORMATION SCI & TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap