AI Paper Atlas

Research map / Point clouds / Point cloud classification

Semantic Privacy Protection with Utility Preservation for 3D Point Clouds

Jinchang Zhang, Jiakai Lin, David Crandall, Guoyu Lu

IJCV 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 1024 input points instead of 512 (ablation)Ours with PointMLP classifier · ScanObjectNNNCRR: 0.781 -> 0.820Improved
use 1024 input points instead of 512 (ablation)Ours with PointMLP classifier · ScanObjectNNOCLR: 0.103 -> 0.080Improved
use 1024 input points instead of 512 (ablation)Ours with PointNet classifier · ModelNet40NCRR: 0.821 -> 0.850Improved
add noise of magnitude 0.005 to the input points (ablation)Ours with PointNet classifier · ScanObjectNNNCRR: 0.651 -> 0.642Hurt
use a stronger classifier (PointMLP instead of PointNet)Ours · ScanObjectNNOCLR: 0.172 -> 0.080Improved
use a stronger classifier (PointMLP instead of PointNet)Ours · ScanObjectNNNCRR: 0.651 -> 0.820Improved
adaptive attacker retrains classifier instead of fixed attackerOurs with PointMLP classifier · ScanObjectNNoriginal-label rate: 0.080 -> 0.098Hurt
class-transfer encryption instead of optical chaotic encryptionPointMLP on ScanObjectNN · ScanObjectNNaccuracy trained in encrypted domain: 0.099 -> 0.840Improved
class-transfer encryption instead of hybrid key encryptionPointMLP on ScanObjectNN · ScanObjectNNaccuracy trained in encrypted domain: 0.349 -> 0.840Improved
class-transfer encryption instead of UMT (permuted-wise test set)PointMLP on ScanObjectNN · ScanObjectNNaccuracy trained in encrypted domain: 0.329 -> 0.840Improved
class-transfer encryption instead of UMT (class-wise test set)PointMLP on ScanObjectNN · ScanObjectNNaccuracy trained in encrypted domain: 0.939 -> 0.840Hurt
class-transfer encryption instead of UMT (class-wise test set)PointMLP on ScanObjectNN · ScanObjectNNaccuracy of original-trained classifier on encrypted data: 0.493 -> 0.119Improved

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