相关论文: On Adversarial Robustness of 3D Point Cloud Classi…

Adversarial attacks have been shown to be highly effective at degrading the performance of deep neural networks (DNNs). The most prominent defense is adversarial training, a method for learning a robust model. Nevertheless, adversarial…

We present a novel approach to point set registration which is based on one-shot adversarial learning. The idea of the algorithm is inspired by recent successes of generative adversarial networks. Treating the point clouds as…

As 3D point cloud analysis has received increasing attention, the insufficient scale of point cloud datasets and the weak generalization ability of networks become prominent. In this paper, we propose a simple and effective augmentation…

Rapid progress in 3D semantic segmentation is inseparable from the advances of deep network models, which highly rely on large-scale annotated data for training. To address the high cost and challenges of 3D point-level labeling, we present…

We study the problem of attribute compression for large-scale unstructured 3D point clouds. Through an in-depth exploration of the relationships between different encoding steps and different attribute channels, we introduce a deep…

Point cloud stands as the most widely adopted format for representing 3D shapes and scenes due to its simplicity and geometric fidelity. However, its inherent unordered and irregular nature, exacerbated by sensor noise and occlusions,…

Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems e.g., for classification, segmentation and object detection. The vulnerability of DNNs against such attacks can prove a major roadblock…

Adversarial training (AT) is currently one of the most effective ways to obtain the robustness of deep neural networks against adversarial attacks. However, most AT methods suffer from robust overfitting, i.e., a significant generalization…

It is well known that adversarial attacks can fool deep neural networks with imperceptible perturbations. Although adversarial training significantly improves model robustness, failure cases of defense still broadly exist. In this work, we…

Our research aims to unify existing works' diverging opinions on how architectural components affect the adversarial robustness of CNNs. To accomplish our goal, we synthesize a suite of three generalizable robust architectural design…

The reconstruction of real-world surfaces is on high demand in various applications. Most existing reconstruction approaches apply 3D scanners for creating point clouds which are generally sparse and of low density. These points clouds will…

Robust imitation learning for robot manipulation requires comprehensive 3D perception, yet many existing methods struggle in cluttered environments. Fixed camera view approaches are vulnerable to perspective changes, and 3D point cloud…

Adversarial training (AT) can help improve the robustness of Vision Transformers (ViT) against adversarial attacks by intentionally injecting adversarial examples into the training data. However, this way of adversarial injection inevitably…

Adversarial training (AT) is a simple yet effective defense against adversarial attacks to image classification systems, which is based on augmenting the training set with attacks that maximize the loss. However, the effectiveness of AT as…

Cloud computing environments are increasingly vulnerable to security threats such as distributed denial-of-service (DDoS) attacks and SQL injection. Traditional security mechanisms, based on rule matching and feature recognition, struggle…

With the development of the 3D data acquisition facilities, the increasing scale of acquired 3D point clouds poses a challenge to the existing data compression techniques. Although promising performance has been achieved in static point…

Point cloud is a crucial representation of 3D contents, which has been widely used in many areas such as virtual reality, mixed reality, autonomous driving, etc. With the boost of the number of points in the data, how to efficiently…

End-to-end trained per-point embeddings are an essential ingredient of any state-of-the-art 3D point cloud processing such as detection or alignment. Methods like PointNet, or the more recent point cloud transformer -- and its variants --…

Deep Neural Networks (DNNs) are known to be vulnerable to adversarial attacks. Currently, there is no clear insight into how slight perturbations cause such a large difference in classification results and how we can design a more robust…

Adversarial attacks and defenses in machine learning and deep neural network have been gaining significant attention due to the rapidly growing applications of deep learning in the Internet and relevant scenarios. This survey provides a…