ShapeAdv: Generating Shape-Aware Adversarial 3D Point Clouds
arXiv:2005.11626
Abstract
We introduce ShapeAdv, a novel framework to study shape-aware adversarial perturbations that reflect the underlying shape variations (e.g., geometric deformations and structural differences) in the 3D point cloud space. We develop shape-aware adversarial 3D point cloud attacks by leveraging the learned latent space of a point cloud auto-encoder where the adversarial noise is applied in the latent space. Specifically, we propose three different variants including an exemplar-based one by guiding the shape deformation with auxiliary data, such that the generated point cloud resembles the shape morphing between objects in the same category. Different from prior works, the resulting adversarial 3D point clouds reflect the shape variations in the 3D point cloud space while still being close to the original one. In addition, experimental evaluations on the ModelNet40 benchmark demonstrate that our adversaries are more difficult to defend with existing point cloud defense methods and exhibit a higher attack transferability across classifiers. Our shape-aware adversarial attacks are orthogonal to existing point cloud based attacks and shed light on the vulnerability of 3D deep neural networks.
3D Point Clouds, Adversarial Learning
References in corpus (15)
- Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
- Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
- Learning Representations and Generative Models for 3D Point Clouds
- Generative and Discriminative Voxel Modeling with Convolutional Neural Networks
- Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision
- Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics
- Defensive Distillation is Not Robust to Adversarial Examples
- Towards the first adversarially robust neural network model on MNIST
- Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning
- The Robust Manifold Defense: Adversarial Training using Generative Models
- Deep Defense: Training DNNs with Improved Adversarial Robustness
- Adversarial Attack and Defense on Point Sets
- DARCCC: Detecting Adversaries by Reconstruction from Class Conditional Capsules
- 3D-LMNet: Latent Embedding Matching for Accurate and Diverse 3D Point Cloud Reconstruction from a Single Image
- Improving Network Robustness against Adversarial Attacks with Compact Convolution