Tingsong Jiang

Papers

Total Citations

H-Index

About

Tingsong Jiang is a researcher whose work sits at the intersection of 3D computer vision and adversarial machine learning, with a particular focus on the security and robustness of point cloud perception systems. His most-cited paper, "Gradient-based sparse voxel attacks on point cloud object detection" (2024), has already garnered 11 citations, reflecting the timely importance of his contributions. In this work, Jiang introduced a novel gradient-based method for crafting sparse adversarial perturbations in voxelized point clouds, effectively exposing vulnerabilities in state-of-the-art 3D object detectors. This research is critical for the safe deployment of autonomous systems, such as self-driving cars, where reliable perception is paramount. By demonstrating how minimal, targeted modifications to LiDAR data can fool detection models, Jiang has advanced the understanding of adversarial robustness in 3D environments. His work bridges the gap between efficient attack strategies and practical defense mechanisms, making him a notable emerging voice in the field. For students and researchers exploring the security of deep learning in spatial domains, Jiang’s contributions offer a clear and impactful entry point into the challenges of safeguarding real-world AI systems.