arXiv 2506.069062025-06-07cs.CV

KNN-Defense：利用最近邻搜索防御3D对抗点云

KNN-Defense: Defense against 3D Adversarial Point Clouds using Nearest-Neighbor Search

University of Waterloo（滑铁卢大学）；University of Tehran（德黑兰大学）；Sharif University of Technology（谢里夫理工大学）

Nima Jamali, Matina Mahdizadeh Sani, Hanieh Naderi, Shohreh Kasaei

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对3D点云面临的点丢弃、偏移和添加等对抗攻击，本文提出基于特征空间最近邻搜索的轻量防御方法KNN-Defense，并在ModelNet40上验证其可显著提升多种分类器鲁棒性。

摘要：

深度神经网络（DNN）在分析3D点云数据方面已展现出卓越性能。然而，它们易受对抗攻击（例如点丢弃、点偏移和点添加）影响的脆弱性，给3D视觉系统的可靠性带来了关键挑战。这些攻击会破坏点云的语义和结构完整性，使许多现有防御机制失效。为解决该问题，本文提出一种名为KNN-Defense的防御策略，其基础是流形假设和特征空间中的最近邻搜索。该方法并不重建表面几何结构或强制实现均匀点分布，而是利用训练集中相邻样本的语义相似性来恢复受扰动输入。KNN-Defense轻量且计算高效，可实现快速推理，适合实时和实际应用。在ModelNet40数据集上的实证结果表明，KNN-Defense在多种攻击类型下显著提升了鲁棒性。特别是在点丢弃攻击下——由于关键点被定向移除，许多现有方法表现不佳——所提方法在PointNet、PointNet++、DGCNN和PCT上分别实现了20.1%、3.6%、3.44%和7.74%的准确率提升。这些发现表明，KNN-Defense为增强3D点云分类器的对抗恢复能力提供了一种可扩展且有效的解决方案。该方法的开源实现（包括代码和数据）可在https://github.com/nimajam41/3d-knn-defense获取。

英文摘要：

Deep neural networks (DNNs) have demonstrated remarkable performance in analyzing 3D point cloud data. However, their vulnerability to adversarial attacks-such as point dropping, shifting, and adding-poses a critical challenge to the reliability of 3D vision systems. These attacks can compromise the semantic and structural integrity of point clouds, rendering many existing defense mechanisms ineffective. To address this issue, a defense strategy named KNN-Defense is proposed, grounded in the manifold assumption and nearest-neighbor search in feature space. Instead of reconstructing surface geometry or enforcing uniform point distributions, the method restores perturbed inputs by leveraging the semantic similarity of neighboring samples from the training set. KNN-Defense is lightweight and computationally efficient, enabling fast inference and making it suitable for real-time and practical applications. Empirical results on the ModelNet40 dataset demonstrated that KNN-Defense significantly improves robustness across various attack types. In particular, under point-dropping attacks-where many existing methods underperform due to the targeted removal of critical points-the proposed method achieves accuracy gains of 20.1%, 3.6%, 3.44%, and 7.74% on PointNet, PointNet++, DGCNN, and PCT, respectively. These findings suggest that KNN-Defense offers a scalable and effective solution for enhancing the adversarial resilience of 3D point cloud classifiers. (An open-source implementation of the method, including code and data, is available at https://github.com/nimajam41/3d-knn-defense).

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。