AI Paper Atlas

Research map / Point clouds / Point cloud classification

Minimal Adversarial Examples for Deep Learning on 3D Point Clouds

Jaeyeon Kim, Binh-Son Hua, Thanh Nguyen, Sai-Kit Yeung

ICCV 2021 · Point clouds › Point cloud classification · approach: Adversarial point cloud attacks · 66 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
replace random near-binary initialisation with critical-point initialisation (ablation)minimal point perturbation attack · ScanObjectNN OBJ_BGattack success rate: 90.16 -> 88.04Hurt
replace random initialisation with critical-point initialisation (ablation)minimal point perturbation attack · ScanObjectNN OBJ_BGChamfer distance: 1.09 x 10^-4 -> 9.53 x 10^-4Hurt
replace random initialisation with critical-point initialisation (ablation)minimal point perturbation attack · ScanObjectNN OBJ_BGnumber of points: 37 -> 29Improved
initialise with all points instead of random points (ablation)minimal point perturbation attack · ScanObjectNN OBJ_BGnumber of points: 37 -> 60Hurt
initialise with all points instead of random points (ablation)minimal point perturbation attack · ScanObjectNN OBJ_BGattack success rate: 90.16 -> 91.12Improved
use the proposed l0-style minimal-point formulation instead of Xiang et al. perturbationPointNet · ModelNet40attack success rate and points: 85.9 -> 89.38 success, 967 -> 36 pointsImproved
use the proposed formulation instead of Xiang et al. point additionPointNet · ModelNet40attack success rate: 73.59 -> 89.01Improved
use the proposed formulation instead of Xiang et al. perturbationPointNet · ScanObjectNN OBJ_BGattack success rate: 81.32 -> 91.72Improved
use the proposed formulation instead of random point selectionPointNet · ModelNet40 point perturbationattack success rate: 55.56 -> 89.38Improved
attack DGCNN instead of PointNetproposed attack · ModelNet40attack success rate: 89.38 -> 62.16Hurt
attack PointASNL instead of PointNetproposed attack · ScanObjectNN OBJ_BGattack success rate: 91.72 -> 55.88Hurt
attack PointNet++ instead of PointNetproposed attack · ScanObjectNN OBJ_BGattack success rate: 91.72 -> 94.05Improved

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