Pith. sign in

REVIEW 6 cited by

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1902.10899 v4 pith:ZM3MAJY5 submitted 2019-02-28 cs.CV cs.AIcs.CRcs.LG

Adversarial Attack and Defense on Point Sets

classification cs.CV cs.AIcs.CRcs.LG
keywords pointattackcloudadversarialdatadefensecloudsproposed
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Emergence of the utility of 3D point cloud data in safety-critical vision tasks (e.g., ADAS) urges researchers to pay more attention to the robustness of 3D representations and deep networks. To this end, we develop an attack and defense scheme, dedicated to 3D point cloud data, for preventing 3D point clouds from manipulated as well as pursuing noise-tolerable 3D representation. A set of novel 3D point cloud attack operations are proposed via pointwise gradient perturbation and adversarial point attachment / detachment. We then develop a flexible perturbation-measurement scheme for 3D point cloud data to detect potential attack data or noisy sensing data. Notably, the proposed defense methods are even effective to detect the adversarial point clouds generated by a proof-of-concept attack directly targeting the defense. Transferability of adversarial attacks between several point cloud networks is addressed, and we propose an momentum-enhanced pointwise gradient to improve the attack transferability. We further analyze the transferability from adversarial point clouds to grid CNNs and the inverse. Extensive experimental results on common point cloud benchmarks demonstrate the validity of the proposed 3D attack and defense framework.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Hard-Label Black-Box Attacks on 3D Point Clouds

    cs.CV 2024-11 unverdicted novelty 7.0

    A spectrum-aware decision boundary algorithm enables effective hard-label black-box adversarial attacks on 3D point cloud models by fusing spectral information across classes and performing curvature-aware iterative o...

  2. Explainability-Aware Frustum Attack: Exposing Structural Vulnerabilities in LiDAR-Based 3D Object Detectors

    cs.CV 2026-06 conditional novelty 6.0

    SALL-guided EFA attacks reduce recall by over 15 points on PointPillars and SECOND using 25-50% fewer frustum perturbations than non-saliency baselines on KITTI and nuScenes.

  3. Explainability-Aware Frustum Attack: Exposing Structural Vulnerabilities in LiDAR-Based 3D Object Detectors

    cs.CV 2026-06 unverdicted novelty 6.0

    The Explainability-aware Frustum Attack (EFA) guided by Saliency-LiDAR (SALL) maps reduces detection recall by more than 15 percentage points using 25-50% fewer perturbed frustums than non-saliency baselines on KITTI ...

  4. Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness

    cs.CV 2026-05 unverdicted novelty 6.0

    MAPR aligns latent and intrinsic geometries in 3D point cloud models via regularization on curvature and diffusion features plus consistency loss, yielding +20% average robustness gains on ModelNet40 without adversari...

  5. Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness

    cs.CV 2026-05 unverdicted novelty 6.0

    MAPR improves adversarial robustness in 3D point cloud networks by aligning latent predictions with intrinsic manifold geometry via curvature/diffusion features and a consistency loss.

  6. Assessing the Operational Impact of Poisoning Attacks over Augmented 3D Point Cloud Public Datasets for Connected and Autonomous Vehicles

    cs.CR 2026-07 conditional novelty 5.0

    GAN-based augmentation of poisoned 3D point cloud datasets amplifies attack effectiveness, increasing misclassification and operational impact on CAV decision-making by up to 3x compared to non-augmented baselines.