Robust Feature-Guided Generative Adversarial Network for Aerial Image Semantic Segmentation against Backdoor Attacks

Robust Feature-Guided Generative Adversarial Network for Aerial Image Semantic Segmentation against Backdoor Attacks

Profiting from the powerful feature extraction and representation capabilities of deep learning (DL), aerial image semantic segmentation based on deep neural networks (DNNs) has achieved remarkable success in recent years. Nevertheless, the security and robustness of DNNs deserve attention when deal...

Full description

Bibliographic Details
Main Authors: Zhen Wang, Buhong Wang, Chuanlei Zhang, Yaohui Liu, Jianxin Guo
Format: Article
Language:English
Published: MDPI AG 2023-05-01
Series:Remote Sensing
Subjects:
aerial images
semantic segmentation
deep neural networks (DNNs)
adversarial machine learning (AML)
backdoor attack
robust feature extraction
Online Access:https://www.mdpi.com/2072-4292/15/10/2580

Internet

https://www.mdpi.com/2072-4292/15/10/2580

Similar Items