论文标题
3D-VFD：针对3D对抗点云的无害探测器
3D-VFD: A Victim-free Detector against 3D Adversarial Point Clouds
论文作者
论文摘要
3D深层模型消耗点云已在计算机视觉中实现了合理的应用效果。但是，最近的研究表明，它们容易受到3D对抗点云的影响。在本文中，我们将这些恶意点云视为3D隐化示例，并提出了一种新的观点，即3D stemanlysis，以对抗此类示例。具体而言，我们建议针对3D对抗点云的3D-VFD，这是一个无害的探测器。它的核心思想是捕获良性点云和对抗点云的残留几何特征分布之间的差异，并将这些点云映射到较低的维空间，在那里我们可以有效地区分它们。与3D对抗点云的现有检测技术不同，3D-VFD不依赖受害者3D DEEP模型的输出来歧视。广泛的实验表明，3D-VFD实现了最新的检测，并且可以根据点添加和点扰动有效地检测3D对抗攻击，同时保持快速检测速度。
3D deep models consuming point clouds have achieved sound application effects in computer vision. However, recent studies have shown they are vulnerable to 3D adversarial point clouds. In this paper, we regard these malicious point clouds as 3D steganography examples and present a new perspective, 3D steganalysis, to counter such examples. Specifically, we propose 3D-VFD, a victim-free detector against 3D adversarial point clouds. Its core idea is to capture the discrepancies between residual geometric feature distributions of benign point clouds and adversarial point clouds and map these point clouds to a lower dimensional space where we can efficiently distinguish them. Unlike existing detection techniques against 3D adversarial point clouds, 3D-VFD does not rely on the victim 3D deep model's outputs for discrimination. Extensive experiments demonstrate that 3D-VFD achieves state-of-the-art detection and can effectively detect 3D adversarial attacks based on point adding and point perturbation while keeping fast detection speed.
