홈 › Papers

Eidos: Efficient, Imperceptible Adversarial 3D Point Clouds

2024-05-23 · Hanwei Zhang, Luo Cheng, Qisong He, Wei Huang, Renjue Li, Ronan Sicre, Xiaowei Huang, Holger Hermanns, Lijun Zhang

Classification of 3D point clouds is a challenging machine learning (ML) task with important real-world applications in a spectrum from autonomous driving and robot-assisted surgery to earth observation from low orbit. As with other ML tasks, classification models are notoriously brittle in the presence of adversarial attacks. These are rooted in imperceptible changes to inputs with the effect that a seemingly well-trained model ends up misclassifying the input. This paper adds to the understanding of adversarial attacks by presenting Eidos, a framework providing Efficient Imperceptible aDversarial attacks on 3D pOint cloudS. Eidos supports a diverse set of imperceptibility metrics. It employs an iterative, two-step procedure to identify optimal adversarial examples, thereby enabling a runtime-imperceptibility trade-off. We provide empirical evidence relative to several popular 3D point cloud classification models and several established 3D attack methods, showing Eidos' superiority with respect to efficiency as well as imperceptibility.

📄 PDF Abstract BibTeX arXiv:2405.14210

Code (0)

등록된 구현이 없습니다.

Tasks

3D Point Cloud Classification Autonomous Driving ClassificationEarth ObservationPoint Cloud Classification

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Geometry-aware Generation of Adversarial and Cooperative Point Clouds

2019-09-25 · Yuxin Wen, Jiehong Lin, Ke Chen, Kui Jia

Recent studies show that machine learning models are vulnerable to adversarial examples. In 2D image domain, these examples are obtained by adding imperceptible noises to natural images. This paper studies adversarial ge…

Fairness Object

Imperceptible Adversarial Attacks on Point Clouds Guided by Point-to-Surface Field

2024-12-26 · Keke Tang, Weiyao Ke, Weilong Peng, Xiaofei Wang 외

Adversarial attacks on point clouds are crucial for assessing and improving the adversarial robustness of 3D deep learning models. Traditional solutions strictly limit point displacement during attacks, making it challen…

Adversarial Robustness Attribute Denoising

Kaleidoscopic Background Attack: Disrupting Pose Estimation with Multi-Fold Radial Symmetry Textures

2025-07-14 · Xinlong Ding, Hongwei Yu, Jiawei Li, Feifan Li 외

Camera pose estimation is a fundamental computer vision task that is essential for applications like visual localization and multi-view stereo reconstruction. In the object-centric scenarios with sparse inputs, the accur…

Camera Pose Estimation Pose Estimation Visual Localization

PWAVEP: Purifying Imperceptible Adversarial Perturbations in 3D Point Clouds via Spectral Graph Wavelets

2026-02-03 · Haoran Li, Renyang Liu, Hongjia Liu, Chen Wang 외 arxiv

Recent progress in adversarial attacks on 3D point clouds, particularly in achieving spatial imperceptibility and high attack performance, presents significant challenges for defenders. Current defensive approaches remai…

Point Clouds

Imperceptible Transfer Attack and Defense on 3D Point Cloud Classification

2021-11-22 · Daizong Liu, Wei Hu

Although many efforts have been made into attack and defense on the 2D image domain in recent years, few methods explore the vulnerability of 3D models. Existing 3D attackers generally perform point-wise perturbation ove…

3D Point Cloud Classification Classification Point Cloud Classification