| Title | Adversarial Robustness Evaluation of Deep Convolutional Neural Network Based SAR ATR Algorithm |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Sun, Hao, Xu, Yanjie, Kuang, Gangyao, Chen, Jin |
| Conference Name | 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS |
| Date Published | jul |
| Keywords | Adversarial robustness, attribution, composability, convolutional neural networks, Deep Learning, Distance measurement, distortion, feature attribution, Geoscience and remote sensing, Human Behavior, Metrics, Perturbation methods, pubcrawl, Robustness, SAR, Target recognition |
| Abstract | Robustness, both to accident and to malevolent perturbations, is a crucial determinant of the successful deployment of deep convolutional neural network based SAR ATR systems in various security-sensitive applications. This paper performs a detailed adversarial robustness evaluation of deep convolutional neural network based SAR ATR models across two public available SAR target recognition datasets. For each model, seven different adversarial perturbations, ranging from gradient based optimization to self-supervised feature distortion, are generated for each testing image. Besides adversarial average recognition accuracy, feature attribution techniques have also been adopted to analyze the feature diffusion effect of adversarial attacks, which promotes the understanding of vulnerability of deep learning models. |
| DOI | 10.1109/IGARSS47720.2021.9554783 |
| Citation Key | sun_adversarial_2021 |
Adversarial Robustness Evaluation of Deep Convolutional Neural Network Based SAR ATR Algorithm