Jay Xiong
Papers
1
Total Citations
16
H-Index
1
About
Jay Xiong is a prominent researcher in the field of adversarial machine learning, with a particular focus on the security and robustness of deep learning-based computer vision systems. His work critically examines the vulnerabilities of object detection algorithms—such as YOLO, R-CNN, and SSD—which are widely deployed in autonomous vehicles, video surveillance, and intelligent robotics. In his highly cited 2018 paper, "Building Towards 'Invisible Cloak': Robust Physical Adversarial Attack on YOLO Object Detector," Xiong pioneered a method to generate physical adversarial patches that can fool state-of-the-art detectors in real-world settings, effectively rendering objects "invisible" to AI systems. This work, garnering 16 citations, has become a foundational reference for research on physical-world adversarial attacks and defenses. Xiong’s contributions are critical for understanding the safety and reliability of AI in high-stakes applications, and his research continues to influence both the academic community and industry practitioners working to build more resilient autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1