Binbin Liu

Papers

Total Citations

H-Index

About

Dr. Binbin Liu is a leading researcher at the forefront of 3D perception and adversarial machine learning, with a focus on securing deep learning systems for real-world applications like autonomous vehicles and robotics. Her seminal work, "The Art of Defense: Letting Networks Fool the Attacker" (2023, 19 citations), introduces a paradigm-shifting approach to safeguarding 3D object classifiers on point cloud data. Rather than merely patching vulnerabilities, Dr. Liu’s research reimagines network defenses by turning the tables on adversaries—designing models that actively mislead attackers while maintaining high accuracy. This contribution addresses a critical gap in the robustness of state-of-the-art (SOTA) 3D perception systems, which are increasingly deployed in safety-critical environments. Her work has already garnered significant attention for its practical implications, offering a blueprint for resilient AI in autonomous navigation and robotic manipulation. Dr. Liu’s innovative blend of defense and deception positions her as a rising authority in trustworthy AI, with her findings shaping how next-generation perception systems are built to withstand real-world threats.