AI Paper Atlas

Research map / Point clouds / Point cloud classification

Shape Prior Guided Attack: Sparser Perturbations on 3D Point Clouds

Zhenbo Shi, Zhi Chen, Zhenbo Xu, Wei Yang, Zhidong Yu, Liusheng Huang

AAAI 2022 · Point clouds › Point cloud classification · approach: Adversarial point cloud attacks · 17 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
Use SPGA instead of AdvPCPoint cloud classifier attacks · ModelNet40, defended classifiersattack success rateImproved
Use SPGA rather than the strongest listed baselineAttacks on PointNet with RO defense · ModelNet40attack success rate: 86.8 -> 87.5Improved
Use SPGA rather than the strongest listed baselineAttacks on PointNet with RS defense · ModelNet40attack success rate: 89.5 -> 88.6Hurt
Add FOFA optimization (ablation)SPGA · Adversarial sample generationgeneration time: 24.47 -> 18.09Improved
Add FOFA optimization (ablation)SPGA · ModelNet40, untargeted attackperturbation budget (%): 4.82 -> 4.36Improved
Allow attaching perturbation points only (SPGA-AT) instead of full SPGA (ablation)SPGA · ModelNet40, defended classifiersattack success rateMixed
Allow dropping original points only (SPGA-DR) instead of full SPGA (ablation)SPGA · ModelNet40, defended classifiersattack success rateMixed
Add FOFA optimization (ablation)SPGA-AT · Adversarial sample generationgeneration time: 24.47 -> 18.63Improved
Add FOFA optimization (ablation)SPGA-DR · Adversarial sample generationgeneration time: 24.03 -> 18.15Improved
Use shape-prior-guided sparse perturbationsSPGA · ModelNet40, untargeted attackperturbation budget (%): 7.64 -> 4.36Improved
Use shape-prior-guided sparse perturbationsSPGA · ModelNet40, untargeted attackperturbation budget (%): 5.29 -> 4.36Improved
Increase the number of SPGA adversarial pointsSPGA · 3D MNISTclassification accuracyHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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