Yulai Xie
Papers
1
Total Citations
2
H-Index
1
About
Yulai Xie is an emerging researcher specializing in adversarial machine learning and 3D computer vision, with a particular focus on the security and robustness of deep learning models applied to three-dimensional data. Their most notable work, "3DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attack" (2023), addresses a critical and underexplored vulnerability in 3D point cloud models — systems that underpin safety-critical technologies such as autonomous driving and robot navigation. By developing a spectrum-based approach to generate decision boundaries under challenging hard-label attack conditions, Xie and their collaborators have pushed the boundaries of what is possible in realistic adversarial threat scenarios, where attackers have minimal access to model internals. This contribution is particularly significant given the rapid maturation of depth sensor technology and the growing deployment of 3D perception systems in real-world environments. Though early in their research career with 2 citations to date, Xie's work tackles a timely and consequential problem at the intersection of AI security and embodied intelligence, positioning them as a researcher to watch as the field of 3D adversarial robustness continues to grow.
Research Focus
Key Achievements
Top Papers
- 1