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

2025-12-15

AI Summary

Existing point-cloud adversarial attacks struggle to simultaneously achieve sparsity (i.e., perturbing few points) and high attack efficacy. Method: This paper proposes a Sparse Collaborative Perturbation (SCP) framework that identifies and perturbs only a small set of critical points, amplifying their collective adversarial effect via joint optimization. We introduce a novel collaborative point selection mechanism grounded in the positive definiteness criterion of local loss-function Hessian blocks, integrated with geometric sensitivity modeling and joint gradient-based optimization. Contribution/Results: The SCP framework achieves 100% attack success rate across mainstream models while reducing the number of perturbed points by 90% compared to state-of-the-art sparse methods. It ensures visual imperceptibility superior to dense attacks and—uniquely—bridges theoretical interpretability (via Hessian-based selection) and practical attack potency, marking the first unified breakthrough in both dimensions.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Adversarial Learning & Robustness
• Search and Optimization: Adversarial Search

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Develops sparse adversarial attacks on point clouds
• Enhances attack effectiveness with minimal point modifications
• Ensures high success rates and improved imperceptibility

Innovation

• Sparse cooperative perturbation framework amplifies adversarial effects
• Selects points via convex loss Hessian block positive-definiteness check
• Optimizes minimal modifications for high-impact imperceptible attacks