Affiliation:
1. College of Electronic Science, National University of Defense Technology, Changsha 410073, China
Abstract
Deep neural networks (DNNs) have been widely utilized in automatic visual navigation and recognition on modern unmanned aerial vehicles (UAVs), achieving state-of-the-art performances. However, DNN-based visual recognition systems on UAVs show serious vulnerability to adversarial camouflage patterns on targets and well-designed imperceptible perturbations in real-time images, which poses a threat to safety-related applications. Considering a scenario in which a UAV is suffering from adversarial attack, in this paper, we investigate and construct two ensemble approaches with CNN and transformer for both proactive (i.e., generate robust models) and reactive (i.e., adversarial detection) adversarial defense. They are expected to be secure under attack and adapt to the resource-limited environment on UAVs. Specifically, the probability distributions of output layers from base DNN models in the ensemble are combined in the proactive defense, which mainly exploits the weak adversarial transferability between the CNN and transformer. For the reactive defense, we integrate the scoring functions of several adversarial detectors with the hidden features and average the output confidence scores from ResNets and ViTs as a second integration. To verify their effectiveness in the recognition task of remote sensing images, we conduct experiments on both optical and synthetic aperture radar (SAR) datasets. We find that the ensemble model in proactive defense performs as well as three popular counterparts, and both of the ensemble approaches can achieve much more satisfactory results than a single base model/detector, which effectively alleviates adversarial vulnerability without extra re-training. In addition, we establish a one-stop platform for conveniently evaluating adversarial robustness and performing defense on recognition models called AREP-RSIs, which is beneficial for the future research of the remote sensing field.
Funder
National Natural Science Foundation of China
Subject
General Earth and Planetary Sciences
Reference91 articles.
1. Deep learning;LeCun;Nature,2015
2. He, H., Wang, S., Yang, D., and Wang, S. (2017, January 20–22). SAR target recognition and unsupervised detection based on convolutional neural network. Proceedings of the 2017 Chinese Automation Congress (CAC), Jinan, China.
3. Multiple Feature Aggregation Using Convolutional Neural Networks for SAR Image-Based Automatic Target Recognition;Cho;IEEE Geosci. Remote Sens. Lett.,2018
4. Few-Shot Class-Incremental SAR Target Recognition Based on Hierarchical Embedding and Incremental Evolutionary Network;Wang;IEEE Trans. Geosci. Remote Sens.,2023
5. An Efficient and Robust Framework for SAR Target Recognition by Hierarchically Fusing Global and Local Features;Ding;IEEE Trans. Image Process.,2018