Random Walks for Adversarial Meshes

A polygonal mesh is the most-commonly used representation of surfaces in computer graphics; thus, a variety of classification networks have been recently proposed. However, while adversarial attacks are wildly researched in 2D, almost no works on adversarial meshes exist. This paper proposes a novel, unified, and general adversarial attack, which leads to misclassification of numerous state-of-the-art mesh classification neural networks. Our attack approach is black-box, i.e. it has access only to the network's predictions, but not to the network's full architecture or gradients. The key idea is to train a network to imitate a given classification network. This is done by utilizing random walks along the mesh surface, which gather geometric information. These walks provide insight onto the regions of the mesh that are important for the correct prediction of the given classification network. These mesh regions are then modified more than other regions in order to attack the network in a manner that is barely visible to the naked eye.