The popularity of point cloud deep models for safety-critical purposes has increased, but the reliability and security of these models can be compromised by intentional or naturally occurring point cloud noise. To combat this issue, we present a novel point cloud outlier removal method called PointCVaR, which empowers standard-trained models to eliminate additional outliers and restore the data. Our approach begins by conducting attribution analysis to determine the influence of each point on the model output, which we refer to as point risk. We then optimize the process of filtering high-risk points using Conditional Value at Risk (CVaR) as the objective. The rationale for this approach is based on the observation that noise points in point clouds tend to cluster in the tail of the risk distribution, with a low frequency but a high level of risk, resulting in significant interference with classification results. Despite requiring no additional training effort, our method produces exceptional results in various removal-and-classification experiments for noisy point clouds, which are corrupted by random noise, adversarial noise, and backdoor trigger noise. Impressively, it achieves 87% accuracy in defense against the backdoor attack by removing triggers. Overall, the proposed PointCVaR effectively eliminates noise points and enhances point cloud classification, making it a promising plug-in module for various models in different scenarios.

翻译：面向安全关键目的的点云深度模型日益普及，但有意或自然产生的点云噪声可能损害这些模型的可靠性与安全性。针对此问题，我们提出一种新颖的点云离群点移除方法PointCVaR，该方法能使标准训练的模型消除多余噪声点并恢复数据。我们首先进行归因分析，以确定每个点对模型输出的影响（称之为点风险）。随后，我们以条件风险价值（CVaR）为目标函数，优化高风险点的过滤过程。该方法的理论基础源于：点云中的噪声点倾向于聚集在风险分布的尾部，虽出现频率低但风险水平高，从而对分类结果造成显著干扰。尽管无需额外训练，我们的方法在随机噪声、对抗噪声及后门触发噪声污染的噪声点云的多项移除-分类实验中均取得卓越效果。令人瞩目的是，通过移除触发噪声，该方法对后门攻击的防御准确率达87%。总体而言，所提出的PointCVaR能高效消除噪声点并增强点云分类性能，可作为适用于不同场景下多种模型的即插即用模块。