Demotivate adversarial defense in remote sensing
This work addresses the problem of network robustness for remote sensing applications, but it is incremental as it tests existing adversarial defenses without proposing new methods.
The paper tackled the problem of whether adversarial defenses improve resilience to over-fitting and geographic variability in remote sensing CNNs, and found through experiments on public datasets that adversarial robustness is uncorrelated with these other forms of robustness.
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.