Papers
2
Total Citations
20
H-Index
2
About
Yunbo Tao is an emerging researcher specializing in adversarial machine learning and 3D computer vision, with a particular focus on the security vulnerabilities of deep learning models applied to three-dimensional data. His most recognized contribution is the development of **3DHacker**, a novel spectrum-based framework for generating adversarial attacks against 3D point cloud models under hard-label black-box settings — one of the most challenging and realistic threat scenarios in the field. This work addresses a critical gap in prior research, which largely relied on white-box access or softer attack assumptions, making 3DHacker especially relevant to real-world applications such as autonomous driving and robot navigation, where adversarial robustness is a safety-critical concern. With approximately 20 citations accumulated since its 2023 publication, the work has quickly attracted attention from the adversarial robustness and 3D perception communities. Tao's research sits at the intersection of point cloud processing, decision boundary estimation, and frequency-domain analysis, offering a fresh perspective on how spectral properties can be exploited to craft imperceptible yet effective perturbations. His contributions are particularly valuable for researchers working to build more secure and reliable perception systems for autonomous platforms.
Research Focus
Key Achievements
Top Papers
- 1
- 2