Skip to main content
Top
Published in: Automatic Control and Computer Sciences 4/2023

01-08-2023

Adversarial Sample Generation Method Based on Global Convolution Noise Reduction Model

Author: Aiping Cai

Published in: Automatic Control and Computer Sciences | Issue 4/2023

Login to get access

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Residual network is a deep learning model widely used in various applications of computer vision, such as image processing, semantic classification and video processing. The traditional residual network is susceptible to the interference induced by the adversarial example attack algorithms, which directly affects the security of practical applications. In this work, we propose a new residual neural network based on a global convolutional denoising model. The global convolution is fused with the denoising technique, and the network structure of the global convolution denoising module is redesigned so that the denoising module can be trained end-to-end with the residual neural network. In addition, the gradient information of the network is concealed to enable the neurons to respond to the pixels that are more meaningful to human vision, thus improving the robustness of the network for adversarial example attack algorithms.
Literature
23.
go back to reference Sankaranarayanan, S., Balaji, Yo., Castillo, C., and Chellappa, R., Generate to adapt: Aligning domains using generative adversarial networks, 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, Salt Lake City, 2018, IEEE, 2018, pp. 8503–8512. https://doi.org/10.1109/cvpr.2018.00887 Sankaranarayanan, S., Balaji, Yo., Castillo, C., and Chellappa, R., Generate to adapt: Aligning domains using generative adversarial networks, 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, Salt Lake City, 2018, IEEE, 2018, pp. 8503–8512. https://​doi.​org/​10.​1109/​cvpr.​2018.​00887
24.
25.
28.
go back to reference Yan, H., Ding, Yu., Li, P., Wang, Q., Xu, Yo., and Zuo, W., Mind the class weight bias: Weighted maximum mean discrepancy for unsupervised domain adaptation, 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Honolulu, 2017, IEEE, 2017, pp. 2272–2281. https://doi.org/10.1109/cvpr.2017.107 Yan, H., Ding, Yu., Li, P., Wang, Q., Xu, Yo., and Zuo, W., Mind the class weight bias: Weighted maximum mean discrepancy for unsupervised domain adaptation, 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Honolulu, 2017, IEEE, 2017, pp. 2272–2281. https://​doi.​org/​10.​1109/​cvpr.​2017.​107
Metadata
Title
Adversarial Sample Generation Method Based on Global Convolution Noise Reduction Model
Author
Aiping Cai
Publication date
01-08-2023
Publisher
Pleiades Publishing
Published in
Automatic Control and Computer Sciences / Issue 4/2023
Print ISSN: 0146-4116
Electronic ISSN: 1558-108X
DOI
https://doi.org/10.3103/S0146411623040028

Other articles of this Issue 4/2023

Automatic Control and Computer Sciences 4/2023 Go to the issue