AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

A Comprehensive Study of the Robustness for LiDAR-Based 3D Object Detectors Against Adversarial Attacks

Yifan Zhang, Junhui Hou, Yixuan Yuan

IJCV 2023 · Adversarial robustness and security › Attacks on text and graphs · approach: Latency and driving-perception attacks · 50 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
add re-voxelization of perturbed points to PGD attack (ablation)PGD point perturbation attack · KITTI SECOND (eps=10cm)mAP ratio (%): 98.63 -> 93.77Improved
add flipped perturbation direction on top of re-voxelization (ablation)PGD point perturbation attack · KITTI SECOND (eps=10cm)mAP ratio (%): 93.77 -> 70.80Improved
add flipped perturbation with large voxel size [0.20,0.20,0.4] (ablation)PGD point perturbation attack · KITTI SECOND (eps=10cm)mAP ratio (%): 89.55 -> 101.78Hurt
re-voxelize perturbed points with small eps, no flipping (ablation)PGD point perturbation attack · KITTI SECOND (eps=7cm)mAP ratio (%): 103.19Hurt
add D_cluster to pillar encoding (ablation)PointPillar · KITTI PGD perturbation (eps=10cm)mAP ratio (%): 64.25 -> 25.24Hurt
add D_center to pillar encoding (ablation)PointPillar · KITTI PGD perturbation (eps=10cm)mAP ratio (%): 64.25 -> 11.59Hurt
use full pillar encoding (both D_cluster and D_center) (ablation)PointPillar · KITTI PGD perturbation (eps=10cm)mAP ratio (%): 64.25 -> 7.28Hurt
change pillar size in x and y (ablation)PointPillar · KITTI PGD perturbation (eps=10cm)mAP ratio (%): 1.76 to 7.53 across sizesNo clear effect
use PGD instead of FGM for point perturbation (iterative vs single step)point perturbation attack · KITTI average over 8 detectorsmAP ratio (%): 70.01 -> 47.29Improved
use cross-task attack from segmentation instead of source PGD attackpoint perturbation attack · KITTI SECONDmAP ratio (%): 70.80 -> 48.09Improved
use cross-task PGD attack instead of source PGD attack on PointPillarpoint perturbation attack · KITTI PointPillarmAP ratio (%): 7.28 -> 80.23Hurt
use PointRCNN as source model for transfer attack instead of SECOND self-attackPGD perturbation · KITTI SECONDmAP ratio (%): 70.80 -> 49.77Improved

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