AI Paper Atlas

Research map / Point clouds / Point cloud classification

FLAT: Flux-aware Imperceptible Adversarial Attacks on 3D Point Clouds

Keke Tang, Lujie Huang, Weilong Peng, Daizong Liu, Xiaofei Wang, Yang Ma, Ligang Liu, Zhihong Tian

ECCV 2024 · Point clouds › Point cloud classification · approach: Adversarial point cloud attacks · 10 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
suppress flux of perturbation vectors in local regions (FLAT)point cloud attacks · ModelNet40 PointNet untargetedChamfer distance (1e-4): 2.747 (ITA) -> 1.539Improved
add flux-based uniformity preservation to IFGM (ablation)IFGM · ModelNet40 PointNetChamfer distance (1e-4): 4.039 -> 2.944Improved
add flux-based uniformity preservation to ITA (ablation)ITA · ModelNet40 PointNetHausdorff distance (1e-2): 0.414 -> 0.579 (CD 2.747 -> 2.253)Mixed
use flux adjustment instead of direct SDM constraint on initial directions (ablation)FLAT · ModelNet40 PointNetChamfer distance (1e-4): 2.502 -> 1.539Improved
use simplified flux instead of formal continuous-field flux (ablation)FLAT · ModelNet40 PointNettime per example (s): 150.07 -> 2.02Improved
choose initial perturbation direction from gradient (IFGM) vs tangent or normal (ablation)FLAT · ModelNet40 PointNetperturbation sizeNo clear effect
increase number of local regions up to 20 (ablation)FLAT · ModelNet40 PointNetl2 and EMDImproved
increase local region radius beyond 0.1 (ablation)FLAT · ModelNet40 PointNetl2 and EMDHurt
apply defenses (SOR, DUP-Net) against FLATFLAT · PointNetattack success rateHurt
transfer FLAT adversarial examples to other classifiersFLAT · PointNet to DGCNN/PointConvattack success rateHurt

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