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

Intelligent model black box watermark trigger set automatic labeling algorithm based on chaos

An automatic labeling and chaotic technology, applied in the field of image processing, can solve problems such as inability to find trigger sets, unpredictable characteristics of chaos, and inability to generalize, so as to solve commercial problems, save manpower and material resources, and ensure the effect of security.

Active Publication Date: 2020-12-25
XIAMEN UNIV TAN KAH KEE COLLEGE
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Machine learning cannot predict the characteristics of chaos, and the attacker cannot find other trigger sets that match the characteristics of our watermark
Therefore, the watermark is not generalizable

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] 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.

[0030] Take the watermark of the intelligent driving-direction control model as an example:

[0031] Taking the intelligent driving-direction intelligent control model as an example, its classification results include four categories: forward, left, right, and stop. In the construction of the model, we first built the driving track of the smart car, and then collected images and labels in all directions as the training data of the model. The flow chart of tri...

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 intelligent model black box watermark trigger set automatic labeling algorithm based on chaos. According to the technology, a problem of automatic labeling of a trigger setlabel is solved by utilizing chaos, and the problem of automatic labeling of an existing black box watermark trigger set can be effectively solved so that a watermark can be extracted by utilizing a small amount of query through a remote API, and an identity of an owner of the deep learning intelligent model is further determined. The problem that the watermark is difficult to extract in a white box watermark scheme can be effectively solved, and a model of a server side does not need to be downloaded or a source program does not need to be read. When judicial evidence is taken, the judicial evidence becomes very simple, and only whether an output classification result conforms to an expected result needs to be compared.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an intelligent model black box watermark trigger set automatic labeling algorithm based on chaos. Background technique [0002] At present, in the development of my country's new generation of artificial intelligence, the Ministry of Science and Technology has initiated the construction of a national new generation of artificial intelligence open innovation platform. Tencent), intelligent voice (HKUST Xunfei Company), etc." The creation of such high-performance deep learning intelligent models requires a lot of manpower and material resources, and they have been deeply integrated with human society. A deep learning intelligent model can be seen as an agent that replaces human work. Therefore, they need to have identity recognition like human beings, providing a basis for identifying the owners and users of deep learning intelligent models. At present, many users do not...

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): G06T1/00
CPCG06T1/005G06T2201/0065
Inventor 张盈谦贾贻然闻芊芊
Owner XIAMEN UNIV TAN KAH KEE COLLEGE
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