paper-with-me

Papers

Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifiers

2019-01-10 · Daniel Liu, Ronald Yu, Hao Su

3D object classification and segmentation using deep neural networks has been extremely successful. As the problem of identifying 3D objects has many safety-critical applications, the neural networks have to be robust against adversarial changes to the input data set. There is a growing body of research on generating human-imperceptible adversarial attacks and defenses against them in the 2D image classification domain. However, 3D objects have various differences with 2D images, and this specific domain has not been rigorously studied so far. We present a preliminary evaluation of adversarial attacks on deep 3D point cloud classifiers, namely PointNet and PointNet++, by evaluating both white-box and black-box adversarial attacks that were proposed for 2D images and extending those attacks to reduce the perceptibility of the perturbations in 3D space. We also show the high effectiveness of simple defenses against those attacks by proposing new defenses that exploit the unique structure of 3D point clouds. Finally, we attempt to explain the effectiveness of the defenses through the intrinsic structures of both the point clouds and the neural network architectures. Overall, we find that networks that process 3D point cloud data are weak to adversarial attacks, but they are also more easily defensible compared to 2D image classifiers. Our investigation will provide the groundwork for future studies on improving the robustness of deep neural networks that handle 3D data.

📄 PDF Abstract BibTeX arXiv:1901.03006

Code (1)

Daniel-Liu-c0deb0t/3D-Neural-Network-Adversarial-Attacks tf

Tasks

3D Object ClassificationGeneral Classificationimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

eToro Customer Care Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Defense-PointNet: Protecting PointNet Against Adversarial Attacks

2020-02-27 · Yu Zhang, Gongbo Liang, Tawfiq Salem, Nathan Jacobs

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 3…

Adversarial Robustness

AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds

2019-12-01 · ECCV 2020 8 · Abdullah Hamdi, Sara Rojas, Ali Thabet, Bernard Ghanem

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…

Adversarial AttackClassify 3D Point Clouds

Nudge Attacks on Point-Cloud DNNs

2020-11-22 · Yiren Zhao, Ilia Shumailov, Robert Mullins, Ross Anderson

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 mod…

Autonomous Driving

Transferable 3D Adversarial Shape Completion using Diffusion Models

2024-07-14 · Xuelong Dai, Bin Xiao

Recent studies that incorporate geometric features and transformers into 3D point cloud feature learning have significantly improved the performance of 3D deep-learning models. However, their robustness against adversari…

3D Point Cloud ClassificationAdversarial AttackPoint Cloud Classification

Geometric Adversarial Attacks and Defenses on 3D Point Clouds

2020-12-10 · Itai Lang, Uriel Kotlicki, Shai Avidan

Deep neural networks are prone to adversarial examples that maliciously alter the network's outcome. Due to the increasing popularity of 3D sensors in safety-critical systems and the vast deployment of deep learning mode…

Adversarial AttackAdversarial Defense