相关论文: 3DHacker: Spectrum-based Decision Boundary Generat…

Trajectory prediction systems are critical for autonomous vehicle safety, yet remain vulnerable to adversarial attacks that can cause catastrophic traffic behavior misinterpretations. Existing attack methods require white-box access with…

Decision-based black-box attacks often necessitate a large number of queries to craft an adversarial example. Moreover, decision-based attacks based on querying boundary points in the estimated normal vector direction often suffer from…

Graph Neural Networks (GNNs) have achieved state-of-the-art performance in various graph structure related tasks such as node classification and graph classification. However, GNNs are vulnerable to adversarial attacks. Existing works…

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…

As the key technology of augmented reality (AR), 3D recognition and tracking are always vulnerable to adversarial examples, which will cause serious security risks to AR systems. Adversarial examples are beneficial to improve the robustness…

Semantic segmentation of 3D LiDAR point clouds, essential for autonomous driving and infrastructure management, is best achieved by supervised learning, which demands extensive annotated datasets and faces the problem of domain shifts. We…

Adversarial attacks exploit the vulnerability of deep models against adversarial samples. Existing point cloud attackers are tailored to specific models, iteratively optimizing perturbations based on gradients in either a white-box or…

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…

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…

Recently, 3D deep learning models have been shown to be susceptible to adversarial attacks like their 2D counterparts. Most of the state-of-the-art (SOTA) 3D adversarial attacks perform perturbation to 3D point clouds. To reproduce these…

We study an important and challenging task of attacking natural language processing models in a hard label black box setting. We propose a decision-based attack strategy that crafts high quality adversarial examples on text classification…

Point clouds provide intrinsic geometric information and surface context for scene understanding. Existing methods for point cloud segmentation require a large amount of fully labeled data. Using advanced depth sensors, collection of large…

The susceptibility of deep neural networks (DNNs) to adversarial examples has prompted an increase in the deployment of adversarial attacks. Image-agnostic universal adversarial perturbations (UAPs) are much more threatening, but many…

Within the past decade, the rise of applications based on artificial intelligence (AI) in general and machine learning (ML) in specific has led to many significant contributions within different domains. The applications range from robotics…

3D point cloud classification requires distinct models from 2D image classification due to the divergent characteristics of the respective input data. While 3D point clouds are unstructured and sparse, 2D images are structured and dense.…

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…

Recent deep networks have achieved good performance on a variety of 3d points classification tasks. However, these models often face challenges in "wild tasks".There are considerable differences between the labeled training/source data…

Decision-based methods have shown to be effective in black-box adversarial attacks, as they can obtain satisfactory performance and only require to access the final model prediction. Gradient estimation is a critical step in black-box…

Manually annotating 3D point clouds is laborious and costly, limiting the training data preparation for deep learning in real-world object detection. While a few previous studies tried to automatically generate 3D bounding boxes from weak…

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…