Explainability-Aware One Point Attack for Point Cloud Neural Networks

by   Hanxiao Tan, et al.

With the proposition of neural networks for point clouds, deep learning has started to shine in the field of 3D object recognition while researchers have shown an increased interest to investigate the reliability of point cloud networks by fooling them with perturbed instances. However, most studies focus on the imperceptibility or surface consistency, with humans perceiving no perturbations on the adversarial examples. This work proposes two new attack methods: opa and cta, which go in the opposite direction: we restrict the perturbation dimensions to a human cognizable range with the help of explainability methods, which enables the working principle or decision boundary of the models to be comprehensible through the observable perturbation magnitude. Our results show that the popular point cloud networks can be deceived with almost 100 input instance. In addition, we attempt to provide a more persuasive viewpoint of comparing the robustness of point cloud models against adversarial attacks. We also show the interesting impact of different point attribution distributions on the adversarial robustness of point cloud networks. Finally, we discuss how our approaches facilitate the explainability study for point cloud networks. To the best of our knowledge, this is the first point-cloud-based adversarial approach concerning explainability. Our code is available at https://github.com/Explain3D/Exp-One-Point-Atk-PC.


page 9

page 16

page 17

page 18

page 19

page 21

page 22

page 23


3D Adversarial Attacks Beyond Point Cloud

Previous adversarial attacks on 3D point clouds mainly focus on add pert...

Visualizing Global Explanations of Point Cloud DNNs

In the field of autonomous driving and robotics, point clouds are showin...

Surrogate Model-Based Explainability Methods for Point Cloud NNs

In the field of autonomous driving and robotics, point clouds are showin...

AssembleRL: Learning to Assemble Furniture from Their Point Clouds

The rise of simulation environments has enabled learning-based approache...

Explainability in Simplicial Map Neural Networks

Simplicial map neural networks (SMNNs) are topology-based neural network...

Shape-invariant 3D Adversarial Point Clouds

Adversary and invisibility are two fundamental but conflict characters o...

Attacking Point Cloud Segmentation with Color-only Perturbation

Recent research efforts on 3D point-cloud semantic segmentation have ach...

Please sign up or login with your details

Forgot password? Click here to reset