Recent research efforts on 3D point cloud semantic segmentation (PCSS) have achieved outstanding performance by adopting neural networks. However, the robustness of these complex models have not been systematically analyzed. Given that PCSS has been applied in many safety-critical applications like autonomous driving, it is important to fill this knowledge gap, especially, how these models are affected under adversarial samples. As such, we present a comparative study of PCSS robustness. First, we formally define the attacker's objective under performance degradation and object hiding. Then, we develop new attack by whether to bound the norm. We evaluate different attack options on two datasets and three PCSS models. We found all the models are vulnerable and attacking point color is more effective. With this study, we call the attention of the research community to develop new approaches to harden PCSS models.

翻译：针对三维点云语义分割（PCSS）的研究工作近期通过采用神经网络取得了显著性能。然而，这些复杂模型的鲁棒性尚未得到系统分析。鉴于PCSS已应用于自动驾驶等安全关键领域，填补这一知识空白——尤其是研究这些模型在对抗样本下的受影响程度——至关重要。为此，我们开展了PCSS鲁棒性的比较研究。首先，我们正式定义了攻击者在性能降级和对象隐藏场景下的目标。随后，我们基于是否对范数进行约束开发了新的攻击方法。我们在两个数据集和三个PCSS模型上评估了不同攻击方案。研究发现所有模型均存在脆弱性，且针对点颜色的攻击更为有效。通过本研究，我们呼吁研究界关注开发新方法以强化PCSS模型。