Related papers: Minimal Adversarial Examples for Deep Learning on …
The wide adaption of 3D point-cloud data in safety-critical applications such as autonomous driving makes adversarial samples a real threat. Existing adversarial attacks on point clouds achieve high success rates but modify a large number…
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…
Recently, deep neural networks have significant progress and successful application in various fields, but they are found vulnerable to attack instances, e.g., adversarial examples. State-of-art attack methods can generate attack images by…
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…
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…
Deep neural networks (DNNs) are vulnerable to adversarial examples that are carefully designed to cause the deep learning model to make mistakes. Adversarial examples of 2D images and 3D point clouds have been extensively studied, but…
3D deep learning has been increasingly more popular for a variety of tasks including many safety-critical applications. However, recently several works raise the security issues of 3D deep models. Although most of them consider adversarial…
We introduce ShapeAdv, a novel framework to study shape-aware adversarial perturbations that reflect the underlying shape variations (e.g., geometric deformations and structural differences) in the 3D point cloud space. We develop…
Self-supervised methods have been proven effective for learning deep representations of 3D point cloud data. Although recent methods in this domain often rely on random masking of inputs, the results of this approach can be improved. We…
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…
3D Point cloud is becoming a critical data representation in many real-world applications like autonomous driving, robotics, and medical imaging. Although the success of deep learning further accelerates the adoption of 3D point clouds in…
In this paper, we introduce a novel conditional generative adversarial network that creates dense 3D point clouds, with color, for assorted classes of objects in an unsupervised manner. To overcome the difficulty of capturing intricate…
Point cloud classifiers with rotation robustness have been widely discussed in the 3D deep learning community. Most proposed methods either use rotation invariant descriptors as inputs or try to design rotation equivariant networks.…
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…
Adversarial examples in machine learning are typically generated using gradients, obtained either directly through access to the model or approximated via queries to it. In this paper, we propose a much simpler approach to craft adversarial…
Point clouds and meshes are widely used 3D data structures for many computer vision applications. While the meshes represent the surfaces of an object, point cloud represents sampled points from the surface which is also the output of…
Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small perturbations of inputs can be sufficient to induce incorrect…
Despite recent success of self-supervised based contrastive learning model for 3D point clouds representation, the adversarial robustness of such pre-trained models raised concerns. Adversarial contrastive learning (ACL) is considered an…
Gradient-based adversarial attacks are widely used to evaluate the robustness of 3D point cloud classifiers, yet they often rely on uniform update rules that neglect point-wise heterogeneity, leading to perceptible perturbations. We propose…
Machine learning models have been shown to be vulnerable to adversarial examples. While most of the existing methods for adversarial attack and defense work on the 2D image domain, a few recent attempts have been made to extend them to 3D…