Adversarial Example in Remote Sensing Image Recognition

TL;DR

This paper investigates the vulnerability of remote sensing image recognition models based on CNNs to adversarial examples, revealing security risks and factors influencing model robustness.

Contribution

It is the first to analyze adversarial examples in RSI recognition under CNN models, demonstrating their vulnerability and factors affecting attack success.

Findings

RSI CNN models are vulnerable to adversarial attacks

Model structure and feature count influence vulnerability

Misclassification relates to class similarity in feature space

Abstract

With the wide application of remote sensing technology in various fields, the accuracy and security requirements for remote sensing images (RSIs) recognition are also increasing. In recent years, due to the rapid development of deep learning in the field of image recognition, RSI recognition models based on deep convolution neural networks (CNNs) outperform traditional hand-craft feature techniques. However, CNNs also pose security issues when they show their capability of accurate classification. By adding a very small variation of the adversarial perturbation to the input image, the CNN model can be caused to produce erroneous results with extremely high confidence, and the modification of the image is not perceived by the human eye. This added adversarial perturbation image is called an adversarial example, which poses a serious security problem for systems based on CNN model recognition results. This paper, for the first time, analyzes adversarial example problem of RSI recognition under CNN models. In the experiments, we used different attack algorithms to fool multiple high-accuracy RSI recognition models trained on multiple RSI datasets. The results show that RSI recognition models are also vulnerable to adversarial examples, and the models with different structures trained on the same RSI dataset also have different vulnerabilities. For each RSI dataset, the number of features also affects the vulnerability of the model. Many features are good for defensive adversarial examples. Further, we find that the attacked class of RSI has an attack selectivity property. The misclassification of adversarial examples of the RSIs are related to the similarity of the original classes in the CNN feature space. In addition, adversarial examples in RSI recognition are of great significance for the security of remote sensing applications, showing a huge potential for future research.