Search Results for author: Jinlai Zhang

Found 5 papers, 4 papers with code

Boosting 3D Adversarial Attacks with Attacking On Frequency

no code implementations26 Jan 2022 Binbin Liu, Jinlai Zhang, Lyujie Chen, Jihong Zhu

Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks.

3D Adversarial Attacks Beyond Point Cloud

1 code implementation25 Apr 2021 Jinlai Zhang, Lyujie Chen, Binbin Liu, Bo Ouyang, Qizhi Xie, Jihong Zhu, Weiming Li, Yanmei Meng

In order to take advantage of the most effective gradient-based attack, a differentiable sample module that back-propagate the gradient of point cloud to mesh is introduced.

Adversarial Attack

The art of defense: letting networks fool the attacker

1 code implementation7 Apr 2021 Jinlai Zhang, Yinpeng Dong, Binbin Liu, Bo Ouyang, Jihong Zhu, Minchi Kuang, Houqing Wang, Yanmei Meng

To this end, in this paper, we propose a novel adversarial defense for 3D point cloud classifier that makes full use of the nature of the DNNs.

Adversarial Defense

PointCutMix: Regularization Strategy for Point Cloud Classification

2 code implementations5 Jan 2021 Jinlai Zhang, Lyujie Chen, Bo Ouyang, Binbin Liu, Jihong Zhu, Yujing Chen, Yanmei Meng, Danfeng Wu

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.

3D Point Cloud Classification Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.