Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifiers
Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifiers
3D object classification 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. We present a preliminary evaluation of adversarial attacks on 3D point cloud classifiers …