Papers
1
Total Citations
16
H-Index
1
About
Riran Cheng is a rising researcher in the field of adversarial machine learning, with a specific focus on 3D computer vision and autonomous systems. His work addresses the critical vulnerability of deep neural networks in safety-critical applications, particularly in 3D object tracking—a core technology for autonomous driving and robotics. In his highly cited 2023 paper, "Topology-aware universal adversarial attack on 3D object tracking," Cheng introduced a novel attack paradigm that exploits the topological structure of 3D point clouds, generating universal perturbations capable of fooling state-of-the-art trackers. This contribution is significant because it reveals a fundamental weakness in how these models perceive spatial relationships, moving beyond traditional pixel-based attacks to a more geometrically aware threat model. With 16 citations in just a short time, his work is already influencing the development of more robust 3D perception systems. Cheng’s research is at the forefront of understanding and mitigating adversarial risks in real-world autonomous systems, making him a key voice in the ongoing effort to secure AI-driven technologies against sophisticated, topology-aware attacks.
Research Focus
Key Achievements
Top Papers
- 1Topology-aware universal adversarial attack on 3D object tracking16 citations · 2023