Image target detection model attack method and device, terminal equipment and storage medium

A target detection and image detection technology, applied in the field of image processing, can solve the problem of low attack strength against samples, and achieve the effect of large attack strength and high disturbance concealment.

Active Publication Date: 2021-01-12
PENG CHENG LAB
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the present invention is to provide an image target detection model attack method, device, termin

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
  • Image target detection model attack method and device, terminal equipment and storage medium
  • Image target detection model attack method and device, terminal equipment and storage medium
  • Image target detection model attack method and device, terminal equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0088] Based on the first embodiment, a second embodiment of the image target detection model attack method of the present invention is proposed. In this example, see image 3 As shown, before step S13, the image target detection model attack method also includes the following steps:

[0089] Step S15: Increase the transparency of the disturbance image.

[0090] In this embodiment, after the disturbance image is generated, in order to improve concealment, the transparency of the disturbance image is increased. It should be understood that the higher the transparency, the more transparent the image. The way of height adjustment can be flexibly set according to actual needs.

[0091] For example, in some embodiments, step S15 includes: increasing the transparency of the disturbance image to a preset transparency threshold. That is to say, a transparency value can be set as the transparency threshold first, and after the disturbed image is generated, the transparency of the di...

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 an image target detection model attack method, and the method comprises the following steps: obtaining a sample image and disturbance image setting information inputted by a user, wherein the disturbance image setting information comprises the size and shape of an image; generating a disturbance image based on the sample image and the disturbance image setting information;generating an adversarial sample based on the sample image and the disturbance image; and inputting the confrontation sample into the image target detection model to be recognized so as to attack theimage target detection model. Since the size and the shape of the disturbance image are set by a user and the user setting has randomness and uncertainty, the difference between the confrontation sample and the sample image is not easy to perceive by naked eyes, the disturbance concealment is high, and the attack intensity is large. The invention further discloses an image target detection model attack device, terminal equipment and a storage medium, the concealment of disturbance is improved, and therefore the attack strength on the image target detection model is improved.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an image target detection model attack method, device, terminal equipment and storage medium. Background technique [0002] With the development of machine learning, image recognition has been continuously improved, and the recognition accuracy has been continuously improved. [0003] However, adding adversarial perturbation to the image can make the image object detection model get completely different results. Therefore, in order to improve the robustness of the image object detection model, it is usually necessary to conduct adversarial attacks on the image object detection model through adversarial examples to improve the robustness of the image object detection model. Different adversarial samples have different attack effects. The stronger the attack, the more robust the image target detection model after the adversarial attack. Therefore, the selection of adversarial exam...

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): G06K9/32G06N20/00
CPCG06N20/00G06V10/25G06V2201/07
Inventor 黄兴森张伟哲束建钢张宾艾建文刘鹏辉
Owner PENG CHENG LAB
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