Less Is More: Sparse and Cooperative Perturbation for Point Cloud Attacks

TL;DR

This paper introduces SCP, a novel sparse and cooperative perturbation method for attacking point clouds, which achieves high success rates with minimal modifications by leveraging joint perturbations of carefully selected points.

Contribution

SCP is the first framework to identify and optimize a subset of points for joint perturbations, significantly improving attack effectiveness and imperceptibility in sparse point cloud attacks.

Findings

Achieves 100% attack success rate on benchmark datasets.

Surpasses state-of-the-art sparse attack methods in effectiveness.

Maintains high imperceptibility with fewer point modifications.

Abstract

Most adversarial attacks on point clouds perturb a large number of points, causing widespread geometric changes and limiting applicability in real-world scenarios. While recent works explore sparse attacks by modifying only a few points, such approaches often struggle to maintain effectiveness due to the limited influence of individual perturbations. In this paper, we propose SCP, a sparse and cooperative perturbation framework that selects and leverages a compact subset of points whose joint perturbations produce amplified adversarial effects. Specifically, SCP identifies the subset where the misclassification loss is locally convex with respect to their joint perturbations, determined by checking the positivedefiniteness of the corresponding Hessian block. The selected subset is then optimized to generate high-impact adversarial examples with minimal modifications. Extensive experiments show that SCP achieves 100% attack success rates, surpassing state-of-the-art sparse attacks, and delivers superior imperceptibility to dense attacks with far fewer modifications.