Deep neural networks (DNNs) have become essential for processing the vast amounts of aerial imagery collected using earth-observing satellite platforms. However, DNNs are vulnerable towards adversarial examples, and it is expected that this weakness also plagues DNNs for aerial imagery. In this work, we demonstrate one of the first efforts on physical adversarial attacks on aerial imagery, whereby adversarial patches were optimised, fabricated and installed on or near target objects (cars) to significantly reduce the efficacy of an object detector applied on overhead images. Physical adversarial attacks on aerial images, particularly those captured from satellite platforms, are challenged by atmospheric factors (lighting, weather, seasons) and the distance between the observer and target. To investigate the effects of these challenges, we devised novel experiments and metrics to evaluate the efficacy of physical adversarial attacks against object detectors in aerial scenes. Our results indicate the palpable threat posed by physical adversarial attacks towards DNNs for processing satellite imagery.

翻译：深神经网络(DNN)对于处理利用地球观测卫星平台收集的大量航空图像至关重要,然而,DNN很容易成为对抗性例子,预计这种弱点也会困扰空中图像的DNN;在这项工作中,我们展示了对空中图像进行人身对抗性攻击的首批努力之一,即对目标物体或近目标物体(汽车)进行最佳的对抗性攻击、制造和安装对抗性补丁,以大大降低对俯冲图像应用的物体探测器的功效;对空中图像,特别是对从卫星平台获取的图像进行实际对抗性攻击,受到大气因素(照明、天气、季节)和观察员与目标之间的距离的挑战;为调查这些挑战的影响,我们设计了新的实验和指标,以评估对空中物体探测器进行实际对抗性攻击的效果;我们的结果表明,对DNNM进行的实际对抗性攻击对DNM进行处理卫星图像构成明显威胁。