arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.03356cs.LG
收藏

可变形网络的泛谱对抗攻击

Universal Spectral Adversarial Attacks for Deformable Shapes

Sapienza University of Rome(罗马第一大学)

Arianna Rampini, Franco Pestarini, Luca Cosmo, Simone Melzi, Emanuele Rodolà

摘要:

众所周知,机器学习模型容易受到对抗攻击的攻击,即数据的扰动,尽管无法感知,但会导致错误的预测。然而,“普遍”攻击的存在(即,在不同数据点之间传递的独特扰动)迄今为止仅对图像进行了证明。部分原因在于缺乏一个通用的域,用于几何数据,如图形,网格和点云,其中可以定义通用的扰动。在本文中,我们提供了一个角度的变化,并证明了存在的几何数据(形状)的通用攻击。我们引入了一个计算过程,完全在谱域中操作,其中的攻击采取小扰动的形式短特征值序列,然后合成通过形状从频谱恢复得到的几何形状。我们的攻击是通用的,因为它们可以跨不同的形状,不同的表示(网格和点云)进行传输,并推广到以前看不见的数据。

英文摘要:

Machine learning models are known to be vulnerable to adversarial attacks, namely perturbations of the data that lead to wrong predictions despite being imperceptible. However, the existence of "universal" attacks (i.e., unique perturbations that transfer across different data points) has only been demonstrated for images to date. Part of the reason lies in the lack of a common domain, for geometric data such as graphs, meshes, and point clouds, where a universal perturbation can be defined. In this paper, we offer a change in perspective and demonstrate the existence of universal attacks for geometric data (shapes). We introduce a computational procedure that operates entirely in the spectral domain, where the attacks take the form of small perturbations to short eigenvalue sequences; the resulting geometry is then synthesized via shape-from-spectrum recovery. Our attacks are universal, in that they transfer across different shapes, different representations (meshes and point clouds), and generalize to previously unseen data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑