Intelligent confrontation sample generation method and system based on optimization algorithm and invariance
A technology against samples and optimization algorithms, applied in neural learning methods, calculations, computer components, etc., can solve problems such as low attack success rate, achieve the effects of improving transferability, improving the generation process, and good application prospects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0031] In order to make the objectives, technical solutions and advantages of the present invention clearer and more comprehensible, the present invention will be described in further detail below with reference to the accompanying drawings and technical solutions.
[0032]Deep neural networks are very vulnerable to adversarial samples, which are generated by adding tiny perturbations to clean images that are barely perceptible to humans, thereby misleading the deep neural network and causing the neural network to give an error Output. Therefore, before the deployment of deep neural networks, adversarial example attacks can be used as an important method to evaluate and improve the robustness of the model. However, under the challenging black-box setting, the attack success rate of most existing adversarial attack methods still needs to be improved. To this end, the embodiment of the present invention provides an intelligent adversarial sample generation method based on an op...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap