Demotivate Adversarial Defense in Remote Sensing

Convolutional neural networks are currently the state-of-the-art algorithms for many remote sensing applications such as semantic segmentation or object detection. However, these algorithms are extremely sensitive to over-fitting, domain change and adversarial examples specifically designed to fool...

Full description

Saved in:
Bibliographic Details
Main Authors: Chan-Hon-Tong, Adrien, Lenczner, Gaston, Plyer, Aurelien
Format: Conference Proceeding
Language:English
Subjects:
Convolutional neural networks
Correlation
Object detection
Remote sensing
Resilience
Robustness
Semantics
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Convolutional neural networks are currently the state-of-the-art algorithms for many remote sensing applications such as semantic segmentation or object detection. However, these algorithms are extremely sensitive to over-fitting, domain change and adversarial examples specifically designed to fool them. While adversarial attacks are not a threat in most remote sensing applications, one could wonder if strengthening networks to adversarial attacks could also increase their resilience to over-fitting and their ability to deal with the inherent variety of worldwide data. In this work, we study both adversarial retraining and adversarial regularization as adversarial defenses to this purpose. However, we show through several experiments on public remote sensing datasets that adversarial robustness seems uncorrelated to geographic and over-fitting robustness.
ISSN:2153-7003
DOI:10.1109/IGARSS47720.2021.9554767