Improving transferability of 3D adversarial attacks with scale and shear transformations

1 code implementation • 2 Nov 2022 • Jinali Zhang, Yinpeng Dong, Jun Zhu, Jihong Zhu, Minchi Kuang, Xiaming Yuan

Extensive experiments show that the SS attack proposed in this paper can be seamlessly combined with the existing state-of-the-art (SOTA) 3D point cloud attack methods to form more powerful attack methods, and the SS attack improves the transferability over 3. 6 times compare to the baseline.

The art of defense: letting networks fool the attacker

1 code implementation • 7 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