Title:
NEURAL NETWORK ROBUSTNESS MEASUREMENT METHOD, AND APPARATUS
Document Type and Number:
WIPO Patent Application WO/2022/062649
Kind Code:
A1
Abstract:
Disclosed are a neural network robustness measurement method and an apparatus. The method comprises: using a neural network and executing a forward operation on a specified sample, and generating a convolution kernel feature map at every convolutional layer;
on each channel, performing sampling and aggregation to form convolutional layer feature maps, and further performing sampling and aggregation to form a sample convolutional map for the specified sample; converting a weight difference in the sample convolutional map into a color difference, so as to visualize the sample convolutional map; extracting a sample having labeling from sample data to serve as a first measurement group, taking a group of a sample feature visualization image and the corresponding specified sample to serve as a second measurement group, and sending a crowd labeling request; and determining the robustness of the neural network on the basis of labeling information of the correctly labeled second measurement group corresponding to the first measurement group in a crowd labeling result. The present invention can correctly assess the robustness of a neural network.
More Like This:
Inventors:
ZHAO RENMING (CN)
Application Number:
PCT/CN2021/109616
Publication Date:
March 31, 2022
Filing Date:
July 30, 2021
Export Citation:
Assignee:
SUZHOU INSPUR INTELLIGENT TECH CO LTD (CN)
International Classes:
G06N3/04
Foreign References:
| CN112232380A | 2021-01-15 | |||
| US20200293834A1 | 2020-09-17 | |||
| CN111488711A | 2020-08-04 |
Other References:
MOOSAVI-DEZFOOLI SEYED-MOHSEN; FAWZI ALHUSSEIN; FROSSARD PASCAL: "DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks", 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), IEEE, 27 June 2016 (2016-06-27), pages 2574 - 2582, XP033021438, DOI: 10.1109/CVPR.2016.282
Attorney, Agent or Firm:
LIAN & LIEN IP ATTORNEYS (CN)
Download PDF: