While deep neural networks (DNNs) achieve impressive performance on environment perception tasks, their sensitivity to adversarial perturbations limits their use in practical applications. In this paper, we (i) propose a novel adversarial perturbation detection scheme based on multi-task perception of complex vision tasks (i.e., depth estimation and semantic segmentation). Specifically, adversarial perturbations are detected by inconsistencies between extracted edges of the input image, the depth output, and the segmentation output. To further improve this technique, we (ii) develop a novel edge consistency loss between all three modalities, thereby improving their initial consistency which in turn supports our detection scheme. We verify our detection scheme's effectiveness by employing various known attacks and image noises. In addition, we (iii) develop a multi-task adversarial attack, aiming at fooling both tasks as well as our detection scheme. Experimental evaluation on the Cityscapes and KITTI datasets shows that under an assumption of a 5% false positive rate up to 100% of images are correctly detected as adversarially perturbed, depending on the strength of the perturbation. Code is available at https://github.com/ifnspaml/AdvAttackDet. A short video at https://youtu.be/KKa6gOyWmH4 provides qualitative results.
翻译:虽然深神经网络(DNNS)在环境认知任务上取得了令人印象深刻的成绩,但它们对对抗性扰动的敏感性限制了其在实际应用中的使用。在本文中,我们(一)提出基于复杂视觉任务(即深度估计和语义分割)的多重任务认识的新颖的对抗性扰动探测机制。具体地说,通过提取输入图像边缘、深度输出和分区输出之间的不一致,可以检测到对抗性扰动。为了进一步改进这一技术,我们(二)在所有三种模式之间形成了新的边缘一致性损失,从而改善了它们最初的一致性,从而反过来支持了我们的探测计划。我们通过使用各种已知的攻击和图像噪音来核查我们的探测计划的有效性。此外,我们(三)制定多任务性对抗性攻击,目的是欺骗两项任务以及我们的探测计划。对城市景象和KITTI数据集的实验性评估表明,在假设5%的假正率下,高达100 %的图像被正确检测为对抗性透视性透度,这取决于 http://HGAng/tqtubas的强度。