Bingzhuo Zhong

Papers

Total Citations

H-Index

About

Bingzhuo Zhong is a researcher at the forefront of safe and trustworthy artificial intelligence, with a primary focus on the formal verification and control of autonomous systems. His work addresses the critical challenge of ensuring reliability in deep neural network (DNN)-based controllers, which are increasingly deployed in high-stakes domains like robotics and autonomous driving. Zhong’s major contribution lies in pioneering a sandboxing framework for DNN-based controllers within stochastic games, a novel approach that allows for rigorous safety guarantees without requiring full formal verification of the complex neural network itself. This work, published in 2023 and already garnering 4 citations, is foundational for the emerging field of safe AI deployment. By bridging the gap between formal methods and practical AI systems, Zhong is enabling a new generation of autonomous systems that can be trusted in uncertain, real-world environments. His research is essential reading for anyone interested in the intersection of machine learning, control theory, and formal verification, and it promises to shape the future of how we certify safety in AI-driven technologies.