轻量级对抗点云净化模块，兼顾防御效果与跨模型迁移能力。
APC: Transferable and Efficient Adversarial Point Counterattack for Robust 3D Point Cloud Recognition
- 通过生成实例化反扰动，从输入层净化点云数据
- 在两个基准上实现顶尖防御性能，且对未见模型有强迁移性
- 无需重训练，推理开销极低，适合实际部署
深度神经网络在3D点云识别中取得显著进展，但仍易受对抗攻击影响。现有防御方法常面临鲁棒性与迁移性之间的权衡。本文提出对抗点云反攻击（APC），一种轻量级输入级净化模块，可为每个点生成特定反扰动，有效中和攻击。APC利用干净-对抗样本对，在数据空间强制几何一致性、在特征空间保持语义一致性。为提升对多样化攻击的泛化能力，采用融合多种攻击类型生成对抗点云的混合训练策略。由于APC仅作用于输入点云，可直接迁移至未见过的模型并防御其对应攻击，无需重新训练。推理时单次前向传播即可获得净化点云，时间与参数开销可忽略不计。在两个3D识别基准上的大量实验表明，APC达到当前最优防御性能。跨模型评估进一步验证其卓越迁移能力。代码已开源：https://github.com/gyjung975/APC。
原文摘要 · Abstract (English)
The advent of deep neural networks has led to remarkable progress in 3D point cloud recognition, but they remain vulnerable to adversarial attacks. Although various defense methods have been studied, they suffer from a trade-off between robustness and transferability. We propose Adversarial Point Counterattack (APC) to achieve both simultaneously. APC is a lightweight input-level purification module that generates instance-specific counter-perturbations for each point, effectively neutralizing attacks. Leveraging clean-adversarial pairs, APC enforces geometric consistency in data space and semantic consistency in feature space. To improve generalizability across diverse attacks, we adopt a hybrid training strategy using adversarial point clouds from multiple attack types. Since APC operates purely on input point clouds, it directly transfers to unseen models and defends against attacks targeting them without retraining. At inference, a single APC forward pass provides purified point clouds with negligible time and parameter overhead. Extensive experiments on two 3D recognition benchmarks demonstrate that the APC achieves state-of-the-art defense performance. Furthermore, cross-model evaluations validate its superior transferability. The code is available at https://github.com/gyjung975/APC.
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。