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 optimization.
Adver- sarialattackanddefenseonpointsets
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
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.
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
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 and nuScenes for detectors like PointPillars and SECOND.
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.
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.
citing papers explorer
-
Hard-Label Black-Box Attacks on 3D Point Clouds
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 optimization.
-
Explainability-Aware Frustum Attack: Exposing Structural Vulnerabilities in LiDAR-Based 3D Object Detectors
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 and nuScenes for detectors like PointPillars and SECOND.
-
Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness
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.
-
Assessing the Operational Impact of Poisoning Attacks over Augmented 3D Point Cloud Public Datasets for Connected and Autonomous Vehicles
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.