Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifiers

10 Jan 2019Daniel LiuRonald YuHao Su

3D object classification and segmentation using deep neural networks has been extremely successful. As the problem of identifying 3D objects has many safety-critical applications, the neural networks have to be robust against adversarial changes to the input data set... (read more)

PDF Abstract

Evaluation Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.