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

Data set protection and verification method based on backdoor attacks

A verification method and data set technology, applied in the Internet field, can solve problems such as being unsuitable for protecting open source data sets

Inactive Publication Date: 2021-02-12
山西三友和智慧信息技术股份有限公司
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the dataset protection methods mentioned above are not suitable for protecting open source datasets

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
  • Data set protection and verification method based on backdoor attacks
  • Data set protection and verification method based on backdoor attacks
  • Data set protection and verification method based on backdoor attacks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0029] A data set protection and verification method based on backdoor attacks, such as figure 1 shown, including the following steps:

[0030] S1. Set the ratio of the watermark γ according to actual needs;

[0031] in: The smaller the γ, the smaller the proportion of the data containing the watermark, and the more concealed the watermark is set. D attack is the attack sample data set, D train is the original data set;

[0032] S2. Divide the original d...

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 technical field of Internet, and particularly relates to a data set protection and verification method based on backdoor attacks, which comprises the following steps: setting the proportion of watermarks gamma according to actual requirements; dividing the original data set into a benign sample data set Dbenign and an attack sample data set Dattack according to gamma;adding watermarks to the attack sample data set Dattack obtained after division, and obtaining a processed attack sample data set Dmodified; and mixing the processed attack sample data set Dmodified with the benign sample data set Dbenign to obtain a watermark data set Dwatermarked. According to the method, attack samples are set by adding triggers to part of the samples, so that when the model istrained by using a standard training process on a watermark data set, a hidden backdoor can be specified while the prediction precision of benign samples is maintained. The method is used for protecting the data set.

Description

technical field [0001] The invention belongs to the technical field of the Internet, and in particular relates to a data set protection and verification method based on a backdoor attack. Background technique [0002] In recent years, deep neural networks have been widely used in various fields. Among them, data sets, especially high-quality open source data sets, are the key factors for the prosperity of deep neural networks. These open-source datasets allow researchers to easily verify the effectiveness of their algorithms or models, and this process, in turn, accelerates the development of deep learning. The collection of data sets consumes a lot of resources, and its value is self-evident, so the existing open source data sets basically require that they can only be used for academic or educational purposes, not for commercial purposes. Based on this background, some dataset protection techniques have been proposed, such as anonymization, encryption and watermarking me...

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): G06F21/16G06T1/00G06N3/08
CPCG06F21/16G06T1/0021G06N3/08
Inventor 潘晓光王小华焦璐璐樊思佳马彩霞
Owner 山西三友和智慧信息技术股份有限公司
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