AI Paper Atlas

Research map / Point clouds / Point cloud classification

Geometry-Aware Generation of Adversarial Point Clouds

Yuxin Wen, Jiehong Lin, Ke Chen, C. L. Philip Chen, Kui Jia

TPAMI 2020 · Point clouds › Point cloud classification · approach: Adversarial point cloud attacks · 143 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 changedWhereMeasuredEffect
add Hausdorff distance term to the geometry-aware regularizer (ablation)GeoA3 · ModelNet40 PointNet, SOR drop 1%attack success rate (%): 24.51 -> 83.47Improved
add local curvature consistency term (ablation)GeoA3 · ModelNet40 PointNet, SOR drop 1%attack success rate (%): 53.85 -> 83.47Improved
add Chamfer distance term (ablation)GeoA3 · ModelNet40 PointNet, SOR drop 1%attack success rate (%): 82.17 -> 83.47Improved
add Hausdorff distance term (ablation)GeoA3 · ModelNet40 PointNetgeometric regularity R (lower better): 0.1588 -> 0.0968Improved
add curvature consistency term (ablation)GeoA3 · ModelNet40 PointNetgeometric regularity R (lower better): 0.1055 -> 0.0968Improved
add Chamfer distance term (ablation)GeoA3 · ModelNet40 PointNetgeometric regularity R (lower better): 0.1020 -> 0.0968Improved
use aggressive misclassification loss instead of margin-based loss (ablation)GeoA3 · ModelNet40 PointNet, SOR drop 20%attack success rate (%): 4.44 -> 11.71Improved
use aggressive misclassification loss instead of margin-based loss (ablation)GeoA3 · ModelNet40 PointNetgeometric regularity R (lower better): 0.0819 -> 0.0968Hurt
replace margin-based loss with aggressive loss (ablation)Xiang et al. · ModelNet40 PointNet, SOR drop 1%attack success rate (%): 1.42 -> 3.21Hurt
replace margin-based loss with aggressive loss (ablation)Xiang et al. · ModelNet40 PointNetgeometric regularity R (lower better): 0.1772 -> 0.1956Hurt
increase number of points from 1,024 to 4,096 (ablation)GeoA3 · ModelNet40 PointNet, SOR drop 10%attack success rate (%): 31.58 -> 22.31No clear effect
vary lambda1 and lambda2 around defaults (ablation)GeoA3 · ModelNet40 PointNetattack success rateNo clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy