Skip to content
Research on adversarial attacks and defenses for deep neural network 3D point cloud classifiers like PointNet and PointNet++.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
src
README.md

README.md

3D Point Cloud Adversarial Attacks and Defenses

Adversarial attacks and defenses on neural networks that process 3D point cloud data, namely PointNet and PointNet++. The preprint paper is available on Arxiv here.

Note that files modified from the PointNet and PointNet++ source codes are included. Some files may need to be moved to the correct location before running experiments.

Highlights

Attacks

  • Fast/iterative gradient sign
  • Jacobian-based saliency map attack
  • Gradient projection
  • Clipping L2 norms

Defenses

  • Adversarial training
  • Outlier removal
  • Salient point removal

Conclusions

  • Adversarial attacks are effective against deep 3D point cloud classifiers
  • It is more easy to defend point cloud classifiers than 2D image classifiers
You can’t perform that action at this time.