改进点云分类的对抗攻击，让扰动更隐蔽更有效。
Rethinking Gradient-based Adversarial Attacks on Point Cloud Classification
- 用加权梯度动态调整每点扰动大小，自适应控制整体扰动强度。
- 将点云分组，只对高攻击效率低感知显著性的组合施加扰动。
- 生成的对抗样本更难察觉，适合研究点云模型鲁棒性的人参考。
基于梯度的对抗攻击广泛用于评估3D点云分类器的鲁棒性，但通常采用统一更新规则，忽视了点间差异，导致扰动明显可见。本文提出两种互补策略： extbf{WAAttack} 使用加权梯度动态调节每点扰动幅度，并采用自适应步长策略控制全局扰动规模； extbf{SubAttack} 将点云划分为子集，在每次迭代中仅扰动具有高对抗效能且低感知显著性的组合。大量实验表明，该方法在生成高度不可察觉的对抗样本方面持续优于现有最优方法。代码已开源：https://github.com/chenjun0326/WA_SubAttack。
原文摘要 · Abstract (English)
Gradient-based adversarial attacks are widely used to evaluate the robustness of 3D point cloud classifiers, yet they often rely on uniform update rules that neglect point-wise heterogeneity, leading to perceptible perturbations. We propose two complementary strategies to improve both the effectiveness and imperceptibility of the attack. \textbf{WAAttack} employs weighted gradients to dynamically adjust per-point perturbation magnitudes and uses an adaptive step size strategy to regulate the global perturbation scale. \textbf{SubAttack} partitions the point cloud into subsets and, at each iteration, perturbs only those combinations with high adversarial efficacy and low perceptual saliency. Together, these methods offer a principled refinement of gradient-based attacks for 3D point clouds. Extensive experiments show that our approach consistently outperforms state-of-the-art methods in generating highly imperceptible adversarial examples. The code is available at https://github.com/chenjun0326/WA_SubAttack.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。