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

Target positioning-based anti-attack method and device, equipment and storage medium

A target positioning and target class technology, applied to equipment and storage media, an anti-attack method based on target positioning, in the field of devices, to achieve the effect of enhancing the attack effect and improving the attack accuracy

Pending Publication Date: 2022-04-08
华润数字科技有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present application provides an anti-attack method, device, equipment and storage medium based on target location to solve the problem of attack accuracy of the attack model in the prior art

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
  • Target positioning-based anti-attack method and device, equipment and storage medium
  • Target positioning-based anti-attack method and device, equipment and storage medium
  • Target positioning-based anti-attack method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057]Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field of this application; the terms used herein in the specification of the application are for the purpose of describing specific embodiments only It is not intended to limit the application; the terms "comprising" and "having" and any variations thereof in the description and claims of this application and the above description of the drawings are intended to cover non-exclusive inclusion. The terms "first", "second" and the like in the description and claims of the present application or the above drawings are used to distinguish different objects, rather than to describe a specific order.

[0058] Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. Th...

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 relates to the technical field of artificial intelligence, and discloses a target positioning-based anti-attack method and device, equipment and a storage medium, and the method comprises the steps: obtaining a to-be-processed image; through an extraction model, performing thermodynamic point extraction on the to-be-processed image to obtain a target class activation thermodynamic diagram corresponding to the to-be-processed image; based on the target class activation thermodynamic diagram, determining the position of the target class; calculating corresponding noise disturbance according to the target class position; after noise disturbance corresponding to the target position is added to the corresponding target class position, multiple iterations are carried out, and a corresponding adversarial sample is obtained; and inputting the confrontation sample into a to-be-attacked model for detection. According to the application, the attack accuracy and the attack effect of the to-be-attacked model are improved.

Description

technical field [0001] The present application relates to the field of artificial intelligence, and in particular, to a method, device, device, and storage medium for an adversarial attack based on target positioning. Background technique [0002] With the increasing development of deep learning technology, the artificial intelligence industry has also made great breakthroughs. The security issues of artificial intelligence models are also increasingly valued by AI practitioners. At this stage, the security issues related to deep learning models also have certain limitations. In the prior art, the attack image is often obtained by directly blurring the image or adding noise in other ways, or using the anchor frame to detect the position of the target category, and simply adding noise to the position to obtain the attack image. The image attacks the detection model, but the solutions of the prior art often have a low attack accuracy. Therefore, how to improve the attack acc...

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): G06K9/62G06N3/04G06N3/08G06V10/764G06V10/40G06V10/30
Inventor 张兴石强刘雨桐王国勋雷晓宇
Owner 华润数字科技有限公司
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