Beibei Yu

Papers

Total Citations

H-Index

About

Beibei Yu is a researcher at the forefront of robotic cybersecurity, with a primary focus on the vulnerabilities of ROS (Robot Operating System)-based platforms. Her work critically examines the intersection of autonomous perception and adversarial threats, particularly in object detection and tracking systems. Yu’s most cited paper, "Data Tampering Attack Design for ROS-Based Object Detection and Tracking Robotic Platform" (2021), stands as a pioneering contribution that systematically demonstrates how malicious data manipulation can compromise a robot’s ability to perceive its environment accurately. By designing and validating attack vectors against camera, radar, and servo motor inputs, she highlights critical security gaps in modern robotic architectures. Though her citation count is currently modest, her research is foundational for the emerging field of robotic adversarial robustness, offering essential insights for developers and security engineers. Yu’s work serves as a vital warning: as robots become more integrated into society, their perceptual systems must be hardened against tampering. Her findings are particularly relevant for autonomous vehicles, industrial robots, and service robotics, where trust in sensor data is paramount.