Related papers: 3D Adversarial Attacks Beyond Point Cloud
Face recognition is a prevailing authentication solution in numerous biometric applications. Physical adversarial attacks, as an important surrogate, can identify the weaknesses of face recognition systems and evaluate their robustness…
Point cloud completion, as the upstream procedure of 3D recognition and segmentation, has become an essential part of many tasks such as navigation and scene understanding. While various point cloud completion models have demonstrated their…
Utilizing 3D point cloud data has become an urgent need for the deployment of artificial intelligence in many areas like facial recognition and self-driving. However, deep learning for 3D point clouds is still vulnerable to adversarial…
Adversarial attacks on point clouds are crucial for assessing and improving the adversarial robustness of 3D deep learning models. Traditional solutions strictly limit point displacement during attacks, making it challenging to balance…
Deep Neural Networks (DNNs) for 3D point cloud recognition are vulnerable to adversarial examples, threatening their practical deployment. Despite the many research endeavors have been made to tackle this issue in recent years, the…
Deep neural networks are vulnerable to adversarial attacks, in which imperceptible perturbations to their input lead to erroneous network predictions. This phenomenon has been extensively studied in the image domain, and has only recently…
Adversarial attack methods based on point manipulation for 3D point cloud classification have revealed the fragility of 3D models, yet the adversarial examples they produce are easily perceived or defended against. The trade-off between the…
Highly expressive models such as deep neural networks (DNNs) have been widely applied to various applications. However, recent studies show that DNNs are vulnerable to adversarial examples, which are carefully crafted inputs aiming to…
Recently, 3D backdoor attacks have posed a substantial threat to 3D Deep Neural Networks (3D DNNs) designed for 3D point clouds, which are extensively deployed in various security-critical applications. Although the existing 3D backdoor…
Deep neural networks for 3D point cloud understanding have achieved remarkable success in object classification and recognition, yet recent work shows that these models remain highly vulnerable to adversarial perturbations. Existing 3D…
Adversary and invisibility are two fundamental but conflict characters of adversarial perturbations. Previous adversarial attacks on 3D point cloud recognition have often been criticized for their noticeable point outliers, since they just…
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 generally perform point-wise perturbation over point clouds,…
Recognizing 3D point cloud plays a pivotal role in many real-world applications. However, deploying 3D point cloud deep learning model is vulnerable to adversarial attacks. Despite many efforts into developing robust model by adversarial…
Classification of 3D point clouds is a challenging machine learning (ML) task with important real-world applications in a spectrum from autonomous driving and robot-assisted surgery to earth observation from low orbit. As with other ML…
Despite remarkable performance across a broad range of tasks, neural networks have been shown to be vulnerable to adversarial attacks. Many works focus on adversarial attacks and defenses on 2D images, but few focus on 3D point clouds. In…
With the maturity of depth sensors, point clouds have received increasing attention in various applications such as autonomous driving, robotics, surveillance, etc., while deep point cloud learning models have shown to be vulnerable to…
In the last few years, the scientific community showed a remarkable and increasing interest towards 3D Virtual Environments, training and testing Machine Learning-based models in realistic virtual worlds. On one hand, these environments…
Studying adversarial attacks on point clouds is essential for evaluating and improving the robustness of 3D deep learning models. However, most existing attack methods are developed under ideal white-box settings and often suffer from…
Transferable adversarial attacks on point clouds remain challenging, as existing methods often rely on model-specific gradients or heuristics that limit generalization to unseen architectures. In this paper, we rethink adversarial…
Robust environment perception is critical for autonomous cars, and adversarial defenses are the most effective and widely studied ways to improve the robustness of environment perception. However, all of previous defense methods decrease…