Adversarial sample generation method and system based on image brightness random transformation
A technology against samples and image brightness, which is applied in the directions of graphic image conversion, image data processing, neural learning methods, etc., can solve the problems of low attack success rate and performance differences, achieve good application prospects, eliminate overfitting, and improve reliability migratory effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0024] In order to make the objects, technical solutions and advantages of the present invention, the present invention will be described in further detail below with reference to the drawings and technical solutions.
[0025] Deep neural networks are fragile to counter-resistance, which is almost unacceptable to add people on the original input image, so that the depth neural network is misused, which brings a threat to the deep neural network. Therefore, before deployment of deep gods, confrontational attacks can be used as an important method for evaluating model robustness. However, in the case of the black box, the attack of the anti-sample is to be improved, that is, the mobility of the sample is also to be improved. In an embodiment of the present invention, a counter-like sample generation method based on image brightness random transformation is provided. See figure 1 As shown, it is used for visual image classification recognition, including the following:
[0026] S101 ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2023 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap