论文标题
开发出不可察觉的对抗斑块，从启用计算机视觉的技术中伪装军事资产
Developing Imperceptible Adversarial Patches to Camouflage Military Assets From Computer Vision Enabled Technologies
论文作者
论文摘要
卷积神经网络（CNN）表现出快速的进展和对象检测的高度成功。但是，最近的证据强调了他们对对抗攻击的脆弱性。这些攻击是计算出导致对象错误分类或检测抑制的图像扰动或对抗斑块。传统的伪装方法是不切实际的，当时将飞机和其他大型移动资产用于智能，监视和侦察技术和第五代导弹中的自主检测。在本文中，我们提出了一种独特的方法，该方法产生了不可察觉的补丁，能够从具有计算机视觉的技术中伪装大量的军事资产。我们通过使对象检测损失最大化，同时限制了贴片的颜色可感知性，从而开发了这些补丁。这项工作还旨在进一步了解对抗性示例及其对对象检测算法的影响。
Convolutional neural networks (CNNs) have demonstrated rapid progress and a high level of success in object detection. However, recent evidence has highlighted their vulnerability to adversarial attacks. These attacks are calculated image perturbations or adversarial patches that result in object misclassification or detection suppression. Traditional camouflage methods are impractical when applied to disguise aircraft and other large mobile assets from autonomous detection in intelligence, surveillance and reconnaissance technologies and fifth generation missiles. In this paper we present a unique method that produces imperceptible patches capable of camouflaging large military assets from computer vision-enabled technologies. We developed these patches by maximising object detection loss whilst limiting the patch's colour perceptibility. This work also aims to further the understanding of adversarial examples and their effects on object detection algorithms.
