Learning Saliency Maps for Adversarial Point-Cloud Generation

by   Tianhang Zheng, et al.

3D point-cloud recognition with deep neural network (DNN) has received remarkable progress on obtaining both high-accuracy recognition and robustness to random point missing (or dropping). However, the robustness of DNNs to maliciously-manipulated point missing is still unclear. In this paper, we show that point-missing can be a critical security concern by proposing a malicious point-dropping method to generate adversarial point clouds to fool DNNs. Our method is based on learning a saliency map for a whole point cloud, which assigns each point a score reflecting its contribution to the model-recognition loss, i.e., the difference between the losses with and without the specific point respectively. The saliency map is learnt by approximating the nondifferentiable point-dropping process with a differentiable procedure of shifting points towards the cloud center. In this way, the loss difference, i.e., the saliency score for each point in the map, can be measured by the corresponding gradient of the loss w.r.t the point under the spherical coordinates. Based on the learned saliency map, maliciously point-dropping attack can be achieved by dropping points with the highest scores, leading to significant increase of model loss and thus inferior classification performance. Extensive evaluations on several state-of-the-art point-cloud recognition models, including PointNet, PointNet++ and DGCNN, demonstrate the efficacy and generality of our proposed saliency-map-based point-dropping scheme. Code for experiments is released on <https://github.com/tianzheng4/Learning-PointCloud-Saliency-Maps>.


page 1

page 2

page 3

page 4


Point Cloud Quality Assessment using 3D Saliency Maps

Point cloud quality assessment (PCQA) has become an appealing research f...

PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples

Point cloud completion, as the upstream procedure of 3D recognition and ...

3D Adversarial Attacks Beyond Point Cloud

Previous adversarial attacks on 3D point clouds mainly focus on add pert...

Benchmarking and Analyzing Robust Point Cloud Recognition: Bag of Tricks for Defending Adversarial Examples

Deep Neural Networks (DNNs) for 3D point cloud recognition are vulnerabl...

Shape-invariant 3D Adversarial Point Clouds

Adversary and invisibility are two fundamental but conflict characters o...

LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networks

Deep neural networks have made tremendous progress in 3D point-cloud rec...

Noise Injection-based Regularization for Point Cloud Processing

Noise injection-based regularization, such as Dropout, has been widely u...

Please sign up or login with your details

Forgot password? Click here to reset