Ronald Yu

Papers

Total Citations

H-Index

About

Ronald Yu is a leading researcher in the field of adversarial machine learning, with a specific focus on the robustness of 3D deep learning systems. His seminal work, "Adversarial Shape Perturbations on 3D Point Clouds" (2020), has garnered 44 citations, establishing him as a key voice in securing 3D vision models. Yu’s major contribution lies in exposing the vulnerability of neural networks that process 3D point cloud data—a critical input for autonomous driving, robotics, and drone control. He demonstrated that subtle, imperceptible shape perturbations could fool state-of-the-art models, highlighting a pressing safety concern for real-world AI applications. By systematically analyzing these adversarial attacks, Yu has laid the groundwork for developing more resilient architectures. His research is particularly notable for bridging the gap between theoretical adversarial examples and practical threats in 3D perception. For students and researchers, Yu’s work serves as a vital reminder that as 3D data becomes ubiquitous, ensuring model robustness is not just an academic exercise but a necessity for trustworthy autonomous systems.