论文标题
传奇：光谱对抗几何攻击3D网眼
SAGA: Spectral Adversarial Geometric Attack on 3D Meshes
论文作者
论文摘要
三角网格是最受欢迎的3D数据表示之一。因此，用于网格处理的深神经网络的部署被广泛传播，并且越来越吸引更多的关注。但是，神经网络容易出现对抗性攻击，精心制作的投入损害了模型的功能。探索这些漏洞的需求是基于3D应用程序未来开发的基本因素。最近，在语义水平上研究了网格攻击，分类器被误导以产生错误的预测。然而，网格表面具有超出其语义含义的复杂几何属性，它们的分析通常包括需要编码和重建形状的几何形状。 我们提出了一个新的框架，用于对3D网状自动编码器的几何对抗攻击。在这种情况下，对抗性输入网格通过迫使其在输出时重建不同的几何形状来欺骗自动编码器。恶意输入是通过在光谱域中扰动干净形状而产生的。我们的方法利用网格的光谱分解以及其他与网格相关的特性，以获得视觉可信的结果，这些结果考虑了表面扭曲的美味。我们的代码可在https://github.com/stoliktomer/saga上公开获取。
A triangular mesh is one of the most popular 3D data representations. As such, the deployment of deep neural networks for mesh processing is widely spread and is increasingly attracting more attention. However, neural networks are prone to adversarial attacks, where carefully crafted inputs impair the model's functionality. The need to explore these vulnerabilities is a fundamental factor in the future development of 3D-based applications. Recently, mesh attacks were studied on the semantic level, where classifiers are misled to produce wrong predictions. Nevertheless, mesh surfaces possess complex geometric attributes beyond their semantic meaning, and their analysis often includes the need to encode and reconstruct the geometry of the shape. We propose a novel framework for a geometric adversarial attack on a 3D mesh autoencoder. In this setting, an adversarial input mesh deceives the autoencoder by forcing it to reconstruct a different geometric shape at its output. The malicious input is produced by perturbing a clean shape in the spectral domain. Our method leverages the spectral decomposition of the mesh along with additional mesh-related properties to obtain visually credible results that consider the delicacy of surface distortions. Our code is publicly available at https://github.com/StolikTomer/SAGA.
