AI Paper Atlas

Research map / Point clouds / Point cloud classification

Imperceptible Transfer Attack and Defense on 3D Point Cloud Classification

Daizong Liu, Wei Hu

TPAMI 2022 · Point clouds › Point cloud classification · approach: Adversarial point cloud attacks · 82 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 adversarial transformation model (ablation)ITA attack, PointNet to PointNet++ · ModelNet40 transfertransfer success rate (%): 14.60 -> 54.62Improved
add adversarial transformation model (ablation)ITA attack, DGCNN to PointNet++ · ModelNet40 transfertransfer success rate (%): 29.89 -> 76.74Improved
replace learning-free cloud-wise transform with learned transformation (ablation)ITA attack, PointNet to PointNet++ · ModelNet40 transfertransfer success rate (%): 31.28 -> 54.62Improved
use point-wise instead of cloud-wise learning-free transformation (ablation)ITA attack, PointNet to PointNet++ · ModelNet40 transfertransfer success rate (%): 31.28 -> 38.41Improved
replace learning-free point-wise transform with learned transformation (ablation)ITA attack, PointNet to PointNet++ · ModelNet40 transfertransfer success rate (%): 38.41 -> 54.62Improved
perturb along normal direction with bounded width vs GeoA xyz perturbationITA vs GeoA, PointNet · ModelNet40, budget B=0.01attack success rate (%): 79% -> 93%Improved
perturb along normal direction with bounded width vs GeoA xyz perturbationITA vs GeoA, PointNet · ModelNet40 perturbation sizegeometric distortion D_m: 0.1243 -> 0.0927Improved
tighten bound width to B=0.01 (ablation)ITA, PointNet · ModelNet40attack success rate (%): 93% at B=0.01, 100% at B=0.02Mixed
ITA instead of GeoA against IF-DefensePointNet · ModelNet40attack success rate (%): 38.72 -> 69.32Improved
add normal-direction Gaussian noise 2% as defense (ablation)ITA, PointNet · ModelNet40attack success rate (%): 100 -> 95.72No clear effect
add latent intra- and inter-class constraint to adversarial training (ablation)Defense, ITA transfer to PointNet · ModelNet40attack success rate (%): 49.98 -> 18.13Improved
add latent constraint versus DeepSym adversarial trainingDefense, ITA transfer to PointNet · ModelNet40attack success rate (%): 37.38 -> 18.13Improved

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