AI Paper Atlas

Research map / Point clouds / Point cloud classification

Certified L2-Norm Robustness of 3D Point Cloud Recognition in the Frequency Domain

Liang Zhou, Qiming Wang, Tianze Chen

AAAI 2026 · Point clouds › Point cloud classification · approach: Adversarial point cloud attacks · 0 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 FreqCert instead of randomized smoothingcertified defense (DGCNN) · ModelNet40certified radius: RS certifies nothing beyond eps=0.02; FreqCert up to eps=0.12Improved
use FreqCert instead of randomized smoothingempirical defense · ModelNet40 (PGD)empirical accuracy: RS collapses beyond eps=0.4; FreqCert over 70% at eps=1.0Improved
use FreqCert instead of IF-Defense under AdvPCCurveNet · ModelNet40 (AdvPC eps=1.25)empirical accuracy (%): 57.9 -> 73.3Improved
use FreqCert instead of DUP-Net under PGDPointNet · ModelNet40 (PGD eps=1.25)empirical accuracy (%): 74.8 -> 78.9Improved
increase number of slices m from 8 to 32 (ablation)FreqCert · ModelNet40certified accuracyImproved
increase number of slices m from 32 to 64 (ablation)FreqCert · ModelNet40certified accuracyNo clear effect
use larger slices n=256 instead of n=32 (ablation)FreqCert · ModelNet40certified accuracy: certificate vanishes near eps=0.08 (n=256) vs 0.14 (n=32)Mixed
use DGCNN instead of PointNet backbone (ablation)FreqCert · ModelNet40certified accuracy: gap typically below 2%No clear effect

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