Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients: Paper and Code

Get our free extension to see links to code for papers anywhere online!Free add-on: code for papers everywhere!Free add-on: See code for papers anywhere!

Add to Chrome

Add to Firefox

Add to Edge

Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients

Mar 29, 2022
Kaidong Li, Ziming Zhang, Cuncong Zhong, Guanghui Wang

Figure 1 for Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients

Figure 2 for Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients

Figure 3 for Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients

Figure 4 for Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients

Share this with someone who'll enjoy it:

Deep neural networks for 3D point cloud classification, such as PointNet, have been demonstrated to be vulnerable to adversarial attacks. Current adversarial defenders often learn to denoise the (attacked) point clouds by reconstruction, and then feed them to the classifiers as input. In contrast to the literature, we propose a family of robust structured declarative classifiers for point cloud classification, where the internal constrained optimization mechanism can effectively defend adversarial attacks through implicit gradients. Such classifiers can be formulated using a bilevel optimization framework. We further propose an effective and efficient instantiation of our approach, namely, Lattice Point Classifier (LPC), based on structured sparse coding in the permutohedral lattice and 2D convolutional neural networks (CNNs) that is end-to-end trainable. We demonstrate state-of-the-art robust point cloud classification performance on ModelNet40 and ScanNet under seven different attackers. For instance, we achieve 89.51% and 83.16% test accuracy on each dataset under the recent JGBA attacker that outperforms DUP-Net and IF-Defense with PointNet by ~70%. Demo code is available at https://zhang-vislab.github.io.

View paper on

Share this with someone who'll enjoy it: