Neil Zhenqiang Gong

Papers

Total Citations

H-Index

About

Neil Zhenqiang Gong is a prominent researcher specializing in the security and robustness of machine learning systems, with a particular focus on adversarial attacks and defenses in safety-critical applications. His work sits at the intersection of artificial intelligence and cybersecurity, addressing vulnerabilities that could have real-world consequences in domains such as autonomous driving and robotic grasping. Gong is perhaps best recognized for his development of **PointGuard**, a provably robust framework for 3D point cloud classification. This contribution directly tackles the challenge of adversarial manipulation — where subtle, carefully crafted perturbations can cause classifiers to produce incorrect predictions — offering theoretical guarantees of robustness that go beyond empirical defenses. With over 60 citations, PointGuard has established itself as a significant reference point in the field of trustworthy 3D perception systems. His research carries meaningful implications for the deployment of AI in high-stakes environments, where classification errors can translate into physical harm. By grounding defenses in formal provability rather than heuristic methods, Gong's work advances a more rigorous standard for evaluating machine learning security, making his contributions essential reading for researchers and practitioners concerned with building reliable, attack-resistant AI systems.