Recent progress in adversarial attacks on 3D point clouds, particularly in achieving spatial imperceptibility and high attack performance, presents significant challenges for defenders. Current defensive approaches remain cumbersome, often requiring invasive model modifications, expensive training procedures or auxiliary data access. To address these threats, in this paper, we propose a plug-and-play and non-invasive defense mechanism in the spectral domain, grounded in a theoretical and empirical analysis of the relationship between imperceptible perturbations and high-frequency spectral components. Building upon these insights, we introduce a novel purification framework, termed PWAVEP, which begins by computing a spectral graph wavelet domain saliency score and local sparsity score for each point. Guided by these values, PWAVEP adopts a hierarchical strategy, it eliminates the most salient points, which are identified as hardly recoverable adversarial outliers. Simultaneously, it applies a spectral filtering process to a broader set of moderately salient points. This process leverages a graph wavelet transform to attenuate high-frequency coefficients associated with the targeted points, thereby effectively suppressing adversarial noise. Extensive evaluations demonstrate that the proposed PWAVEP achieves superior accuracy and robustness compared to existing approaches, advancing the state-of-the-art in 3D point cloud purification. Code and datasets are available at https://github.com/a772316182/pwavep

翻译：近年来，三维点云对抗攻击领域取得的进展，特别是在实现空间不可察觉性与高攻击性能方面，给防御者带来了严峻挑战。现有的防御方法通常较为繁琐，往往需要对模型进行侵入式修改、依赖昂贵的训练过程或辅助数据访问。为应对这些威胁，本文提出一种基于谱域的即插即用非侵入式防御机制，其理论基础源于对不可察觉扰动与高频谱分量之间关系的理论与实证分析。基于这些发现，我们提出了一种新颖的净化框架PWAVEP。该框架首先计算每个点的谱图小波域显著性分数与局部稀疏性分数，并以此为指导采用分层处理策略：一方面剔除被识别为难以恢复的对抗性离群点的最显著点；同时对更广泛的中等显著性点集实施谱滤波处理。该过程利用图小波变换衰减目标点对应的高频系数，从而有效抑制对抗噪声。大量实验评估表明，相较于现有方法，所提出的PWAVEP在精度与鲁棒性方面均取得更优性能，推动了三维点云净化技术的进展。代码与数据集已发布于 https://github.com/a772316182/pwavep