DeepAI AI Chat
Log In Sign Up

Random Walks for Adversarial Meshes

by   Amir Belder, et al.

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.


page 6

page 7


AttWalk: Attentive Cross-Walks for Deep Mesh Analysis

Mesh representation by random walks has been shown to benefit deep learn...

MeshWalker: Deep Mesh Understanding by Random Walks

Most attempts to represent 3D shapes for deep learning have focused on v...

SAGA: Spectral Adversarial Geometric Attack on 3D Meshes

A triangular mesh is one of the most popular 3D data representations. As...

Pixle: a fast and effective black-box attack based on rearranging pixels

Recent research has found that neural networks are vulnerable to several...

Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition

Face recognition is a prevailing authentication solution in numerous bio...

Attention Mesh: High-fidelity Face Mesh Prediction in Real-time

We present Attention Mesh, a lightweight architecture for 3D face mesh p...

Recovering Localized Adversarial Attacks

Deep convolutional neural networks have achieved great successes over re...