Generating 3D Adversarial Point Clouds
Explore this paper's citation graph
- Type
- preprint
- Published
- 2018-09-19
- Cited by
- 391
- References
- 46
- Access
- Open access
- OpenAlex
- https://openalex.org/W2889986026
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:52302013
Keywords
Adversarial system, Point cloud, Computer science, Deep neural networks, Point (geometry)
References
- Intriguing properties of neural networks
- Gradient-based learning applied to document recognition
- The Limitations of Deep Learning in Adversarial Settings
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks
- Orientation-boosted Voxel Nets for 3D Object Recognition
- Adversarial examples in the physical world
- Towards Evaluating the Robustness of Neural Networks
- Defensive Distillation is Not Robust to Adversarial Examples
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
- A Point Set Generation Network for 3D Object Reconstruction from a Single Image
- A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise
- Practical Black-Box Attacks against Machine Learning
- Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
- MagNet: A Two-Pronged Defense against Adversarial Examples
- PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
- Fast segmentation of 3D point clouds: A paradigm on LiDAR data for autonomous vehicle applications
- Robust Physical-World Attacks on Machine Learning Models
- ComplementMe
- Robust Physical-World Attacks on Deep Learning Models
- Frustum PointNets for 3D Object Detection from RGB-D Data
Cited by
- Learning Saliency Maps for Adversarial Point-Cloud Generation
- SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications
- Deflecting 3D Adversarial Point Clouds Through Outlier-Guided Removal
- Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifiers
- Adversarial Attack and Defense on Point Sets
- Enhancing ML Robustness Using Physical-World Constraints
- Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving
- Adversarial Objects Against LiDAR-Based Autonomous Driving Systems
- Structure-Invariant Testing for Machine Translation
- Adversarial point perturbations on 3D objects
- Curb Detection and Tracking in Low-Resolution 3D Point Clouds Based on Optimization Framework
- DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense
- SMART: Skeletal Motion Action Recognition aTtack
- Smoothed Inference for Adversarially-Trained Models
- Visualizing point cloud classifiers by curvature smoothing
- Rearchitecting Classification Frameworks For Increased Robustness
- SampleNet: Differentiable Point Cloud Sampling
- SKD: Unsupervised Keypoint Detecting for Point Clouds using Embedded Saliency Estimation
- Adversarial Attacks and Defenses in Deep Learning
- Geometry-aware Generation of Adversarial and Cooperative Point Clouds
Related papers
- Global Adversarial Attacks for Assessing Deep Learning Robustness
- Developing and Defeating Adversarial Examples
- Generating adversarial examples for DNN using pooling layers
- Adversarial Perturbation Defense on Deep Neural Networks
- A Brief Comparison Between White Box, Targeted Adversarial Attacks in Deep Neural Networks
- Efficient Defenses Against Adversarial Attacks