Cage-Based Deformation for Transferable and Undefendable Point Cloud Attack

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Keke, Du, Ziyong, Peng, Weilong, Wang, Xiaofei, Zhu, Peican, Liu, Ligang, Tian, Zhihong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912459540922368
author Tang, Keke
Du, Ziyong
Peng, Weilong
Wang, Xiaofei
Zhu, Peican
Liu, Ligang
Tian, Zhihong
author_facet Tang, Keke
Du, Ziyong
Peng, Weilong
Wang, Xiaofei
Zhu, Peican
Liu, Ligang
Tian, Zhihong
contents Adversarial attacks on point clouds often impose strict geometric constraints to preserve plausibility; however, such constraints inherently limit transferability and undefendability. While deformation offers an alternative, existing unstructured approaches may introduce unnatural distortions, making adversarial point clouds conspicuous and undermining their plausibility. In this paper, we propose CageAttack, a cage-based deformation framework that produces natural adversarial point clouds. It first constructs a cage around the target object, providing a structured basis for smooth, natural-looking deformation. Perturbations are then applied to the cage vertices, which seamlessly propagate to the point cloud, ensuring that the resulting deformations remain intrinsic to the object and preserve plausibility. Extensive experiments on seven 3D deep neural network classifiers across three datasets show that CageAttack achieves a superior balance among transferability, undefendability, and plausibility, outperforming state-of-the-art methods. Codes will be made public upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2507_00690
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cage-Based Deformation for Transferable and Undefendable Point Cloud Attack
Tang, Keke
Du, Ziyong
Peng, Weilong
Wang, Xiaofei
Zhu, Peican
Liu, Ligang
Tian, Zhihong
Computer Vision and Pattern Recognition
Cryptography and Security
Adversarial attacks on point clouds often impose strict geometric constraints to preserve plausibility; however, such constraints inherently limit transferability and undefendability. While deformation offers an alternative, existing unstructured approaches may introduce unnatural distortions, making adversarial point clouds conspicuous and undermining their plausibility. In this paper, we propose CageAttack, a cage-based deformation framework that produces natural adversarial point clouds. It first constructs a cage around the target object, providing a structured basis for smooth, natural-looking deformation. Perturbations are then applied to the cage vertices, which seamlessly propagate to the point cloud, ensuring that the resulting deformations remain intrinsic to the object and preserve plausibility. Extensive experiments on seven 3D deep neural network classifiers across three datasets show that CageAttack achieves a superior balance among transferability, undefendability, and plausibility, outperforming state-of-the-art methods. Codes will be made public upon acceptance.
title Cage-Based Deformation for Transferable and Undefendable Point Cloud Attack
topic Computer Vision and Pattern Recognition
Cryptography and Security
url https://arxiv.org/abs/2507.00690