Boosting Adversarial Transferability via Gradient Relevance Attack

2 code implementations • ICCV 2023 • Hegui Zhu, Yuchen Ren, Xiaoyan Sui, Lianping Yang, Wuming Jiang

Plentiful adversarial attack researches have revealed the fragility of deep neural networks (DNNs), where the imperceptible perturbations can cause drastic changes in the output.

Adversarial Attack

Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densities

1 code implementation • 5 Dec 2022 • Qi Wang, Sheng Shi, Jiahui Li, Wuming Jiang, Xiangde Zhang

Existing methods are limited by the inconsistent point densities of different parts in the point cloud.