通过频谱图小波净化3D点云中的不可察觉攻击扰动
PWAVEP: Purifying Imperceptible Adversarial Perturbations in 3D Point Clouds via Spectral Graph Wavelets
- 在频谱域分析扰动与高频成分关系，构建可插拔净化框架
- 对高显著性点直接剔除，中等显著性点进行频谱滤波降噪
- 无需模型修改，适用于多种攻击场景，适合防御研究者
近期3D点云对抗攻击在实现空间不可察觉性和高攻击效果方面取得进展，给防御带来严峻挑战。现有防御方法往往需要侵入式模型修改、昂贵训练过程或辅助数据访问。为此，本文提出一种基于频谱域的即插即用非侵入式防御机制，其理论与实证分析揭示了不可察觉扰动与高频谱成分之间的关联。在此基础上，提出新型净化框架PWAVEP：首先为每个点计算频谱图小波域显著性分数与局部稀疏性分数；随后采用分层策略，剔除显著性最高的点（视为难以恢复的对抗异常点），同时对中等显著性点群应用频谱滤波，利用图小波变换抑制与目标点相关的高频系数，有效压制对抗噪声。大量实验表明，所提PWAVEP在准确率与鲁棒性上均优于现有方法，推动了3D点云净化技术的最新进展。代码与数据集见https://github.com/a772316182/pwavep。
原文摘要 · Abstract (English)
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
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。