Papers
1
Total Citations
17
H-Index
1
About
Zhidong Yu is a leading researcher in the field of 3D computer vision and adversarial machine learning, with a particular focus on the security and robustness of deep neural networks for 3D point cloud data. His most cited work, "Shape Prior Guided Attack: Sparser Perturbations on 3D Point Clouds" (2022, 17 citations), addresses the critical vulnerability of 3D classification models used in autonomous driving, robotics, and drone navigation. Yu introduced a novel attack method that leverages shape priors to generate sparser, more imperceptible adversarial perturbations, exposing fundamental weaknesses in point cloud processing pipelines. This contribution is vital for developing more resilient AI systems in safety-critical applications. His research bridges the gap between geometric deep learning and adversarial robustness, offering both theoretical insights and practical attack strategies. Yu's work has been recognized for its impact on the security of emerging 3D vision technologies, making him a key voice in the ongoing effort to build trustworthy AI for real-world perception tasks.
Research Focus
Key Achievements
Top Papers
- 1Shape Prior Guided Attack: Sparser Perturbations on 3D Point Clouds17 citations · 2022