Hang Lei

University of Electronic Science and Technology of China

Papers

Total Citations

H-Index

About

Hang Lei is a rising researcher in the field of adversarial machine learning, with a particular focus on the security and robustness of 3D perception systems. His work addresses critical vulnerabilities in deep neural networks used for autonomous driving and robotics, specifically targeting 3D object tracking. In his highly cited 2023 paper, “Topology-aware universal adversarial attack on 3D object tracking,” Lei introduced a novel attack paradigm that generates universal perturbations capable of fooling trackers by exploiting the topological structure of 3D point clouds. This contribution, already garnering 16 citations, highlights his ability to bridge theoretical adversarial attack strategies with practical, real-world threats. Beyond this, Lei’s research explores the intersection of geometric deep learning and security, aiming to develop both more effective attacks and robust defenses. His work is notable for its emphasis on universal and transferable adversarial examples, which pose significant challenges to the deployment of safe AI in safety-critical environments. As a young scholar, Hang Lei is establishing himself as a key voice in the emerging dialogue on trustworthy 3D vision, with his findings directly informing the design of more resilient autonomous systems.