Trajectory prediction is a critical component for autonomous vehicles (AVs) to perform safe
planning and navigation. However, few studies have analyzed the adversarial robustness of …

Adversary and invisibility are two fundamental but conflict characters of adversarial
perturbations. Previous adversarial attacks on 3D point cloud recognition have often been …

Although many efforts have been made into attack and defense on the 2D image domain in
recent years, few methods explore the vulnerability of 3D models. Existing 3D attackers …

Recently, several attempts have demonstrated that 3D deep learning models are as
vulnerable to adversarial example attacks as 2D models. However, these methods are still …

Point cloud classification is an essential component in many security-critical applications
such as autonomous driving and augmented reality. However, point cloud classifiers are …

Certified robustness guarantee gauges a model's resistance to test-time attacks and can
assess the model's readiness for deployment in the real world. In this work, we explore a …

The use of deep 3D point cloud models in safety-critical applications, such as autonomous
driving, dictates the need to certify the robustness of these models to real-world …

In this paper, we explore a critical yet under-investigated issue: how to learn robust and well-
generalized 3D representation from pre-trained vision language models such as CLIP …