Research map / Point clouds / Point cloud classification
Robust Adversarial Objects against Deep Learning Models
Read the paperCheck 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 |
|---|---|---|---|
| surface reconstruction with closest-point resampling | adversarial point clouds · ModelNet40 random target, car | attack success rate: 86.25 -> 73.75 | Hurt |
| random resampling of reconstructed mesh instead of closest | adversarial objects · ModelNet40 random target, car | attack success rate: 73.75 -> 2.81 | Hurt |
| voting defense with 10 rotations | PointNet++ vs our attack · ModelNet40 random target | attack success rate: 60.78 -> 29.84 | Hurt |
| kNN outlier removal defense (k=10) | PointNet++ vs our attack · ModelNet40 untargeted | attack success rate: 98.39 | No clear effect |
| kNN outlier removal defense (k=10, alpha=0) | PointNet++ vs our attack · ModelNet40 random target | attack success rate: 43.07 | Hurt |
| larger input points (SSG-2048 vs SSG-1024) | PointNet++ · ModelNet40 random target, sofa | attack success rate: 81.56 -> 59.06 | Mixed |
Closest papers by meaning
- Generating 3D Adversarial Point Clouds (CVPR 2019 · similarity 0.94)
- Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions (NeurIPS 2021 · similarity 0.90)
- A Critical Revisit of Adversarial Robustness in 3D Point Cloud Recognition with Diffusion-Driven Purification (ICML 2023 · similarity 0.90)
- Robustness of 3D Deep Learning in an Adversarial Setting (CVPR 2019 · similarity 0.89)
- Seeing is Not Believing: Adversarial Natural Object Optimization for Hard-Label 3D Scene Attacks (CVPR 2025 · similarity 0.89)
- Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds (CVPR 2024 · similarity 0.88)
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.