Research map / Point clouds / Point cloud classification
PointGuard: Provably Robust 3D Point Cloud Classification
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use PointGuard with subsampling instead of randomized smoothing | PointNet · ModelNet40, point modification, 30 points | certified accuracy: 0% -> 69.7% | Helped |
| Train the classifier on subsampled point clouds rather than original point clouds (ablation) | PointGuard · ModelNet40 | certified accuracy | Helped |
| Reduce subsampling size k (ablation) | PointGuard · ModelNet40 | certified accuracy | Mixed |
| Increase confidence-bound parameter alpha (ablation) | PointGuard · ModelNet40 | certified accuracy | Helped |
| Increase Monte Carlo sample count N (ablation) | PointGuard · ModelNet40 | certified accuracy | Helped |
| Increase alpha or N after they are already large enough (ablation) | PointGuard · ModelNet40 | certified accuracy | No clear effect |
| Use PointGuard rather than randomized smoothing | PointNet · ModelNet40, point modification attacks | certified accuracy | Helped |
| Apply PointGuard to point deletion rather than relying on the empirical deletion attack result | PointNet · ModelNet40, point deletion attacks | accuracy: 76.1% vs. 73.4%; 67.7% vs. 64.3%; 57.7% vs. 53.5% | Mixed |
Closest papers by meaning
- PointCVaR: Risk-Optimized Outlier Removal for Robust 3D Point Cloud Classification (AAAI 2024 · similarity 0.89)
- Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds (CVPR 2024 · similarity 0.88)
- Curvature-Invariant Adversarial Attacks for 3D Point Clouds (AAAI 2024 · similarity 0.87)
- Improving Robustness of 3D Point Cloud Recognition from a Fourier Perspective (NeurIPS 2024 · similarity 0.87)
- Explicitly Perceiving and Preserving the Local Geometric Structures for 3D Point Cloud Attack (AAAI 2024 · similarity 0.87)
- ConcreTizer: Model Inversion Attack via Occupancy Classification and Dispersion Control for 3D Point Cloud Restoration (ICLR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.