Defending against Poisoning Attacks in Aerial Image Semantic Segmentation with Robust Invariant Feature Enhancement

Defending against Poisoning Attacks in Aerial Image Semantic Segmentation with Robust Invariant Feature Enhancement

The outstanding performance of deep neural networks (DNNs) in multiple computer vision in recent years has promoted its widespread use in aerial image semantic segmentation. Nonetheless, prior research has demonstrated the high susceptibility of DNNs to adversarial attacks. This poses significant se...

Full description

Bibliographic Details
Main Authors: Zhen Wang, Buhong Wang, Chuanlei Zhang, Yaohui Liu, Jianxin Guo
Format: Article
Language:English
Published: MDPI AG 2023-06-01
Series:Remote Sensing
Subjects:
aerial images
semantic segmentation
deep neural networks (DNNs)
robust invariant features
poisoning attack
adversarial defense
Online Access:https://www.mdpi.com/2072-4292/15/12/3157

Internet

https://www.mdpi.com/2072-4292/15/12/3157

Similar Items