Cage-Based Deformation for Transferable and Undefendable Point Cloud Attack

TL;DR

CageAttack introduces a cage-based deformation method for generating natural, transferable, and hard-to-defend adversarial point clouds, improving over existing approaches by maintaining plausibility and enhancing attack effectiveness.

Contribution

The paper presents a novel cage-based deformation framework for adversarial point clouds that improves transferability and undefendability while preserving natural appearance.

Findings

Outperforms state-of-the-art methods in transferability and undefendability.

Maintains high plausibility of adversarial point clouds.

Effective across multiple classifiers and datasets.

Abstract

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.