Adversarial sample generation method and device and computer equipment

A technology against samples and samples, applied in computer components, calculations, calculation models, etc., can solve problems such as model error predictions, and achieve the effect of avoiding continuous relaxation problems

Active Publication Date: 2020-06-12
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But when input some adversarial samples maliciously constructed ba

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
  • Adversarial sample generation method and device and computer equipment
  • Adversarial sample generation method and device and computer equipment
  • Adversarial sample generation method and device and computer equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with this specification. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present specification as recited in the appended claims.

[0024] The terms used in this specification are for the purpose of describing particular embodiments only, and are not intended to limit the specification. As used in this specification and the appended claims, the singular forms "a", "the", and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It should also be understood that the t...

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 embodiment of the invention provides an adversarial sample generation method and device and computer equipment. The method includes: determining associated elements of a target node in the graph data sample; modifying the graph data sample according to the associated elements, inputting the modified graph data sample into a target model, determining an interference parameter representing the interference size of each associated element on the target model according to a result output by the target model, and then selecting the target element with relatively large interference to modify thegraph data to obtain an adversarial sample. The disturbance result of the associated element is accurately quantified through forward calculation of the model, the problems of continuous relaxation in calculation of the disturbance result based on gradient information and inaccuracy of the calculated disturbance result are avoided, and the least disturbance is added to the graph-junction data through a greedy selection strategy to generate an adversarial sample.

Description

technical field [0001] This description relates to the technical field of artificial intelligence, and in particular to a method, device and computer equipment for generating an adversarial example. Background technique [0002] With the development of artificial intelligence, machine learning is widely used in more and more scenarios, such as using neural network models to classify text and pictures, and using classification models to detect abnormal users from social networks. Although, for some models, the accuracy of its prediction results is already very high. But when input some adversarial samples maliciously constructed based on normal samples, the model will still make wrong predictions. Using adversarial examples to attack the model can detect potential loopholes in the neural network model, so that the model can be optimized to improve model performance. Therefore, it is necessary to improve the generation method of adversarial samples in order to generate less ...

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): G06K9/62G06N20/00
CPCG06N20/00G06F18/241
Inventor 皇甫志刚任彦昆林建滨梁琛
Owner ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
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