Revisiting Physically Realizable Adversarial Object Attack against LiDAR-based Detection: Clarifying Problem Formulation and Experimental Protocols
This addresses reproducibility issues in adversarial robustness research for LiDAR perception, which is critical for real-world applications like autonomous vehicles, but is incremental as it focuses on standardization rather than a new attack method.
The paper tackles the problem of inconsistent and non-reproducible physical adversarial object attacks against LiDAR-based 3D object detection by proposing a standardized, device-agnostic framework that enables fair comparison and accelerates research, validated by successfully transferring simulated attacks to a physical LiDAR system.
Adversarial robustness in LiDAR-based 3D object detection is a critical research area due to its widespread application in real-world scenarios. While many digital attacks manipulate point clouds or meshes, they often lack physical realizability, limiting their practical impact. Physical adversarial object attacks remain underexplored and suffer from poor reproducibility due to inconsistent setups and hardware differences. To address this, we propose a device-agnostic, standardized framework that abstracts key elements of physical adversarial object attacks, supports diverse methods, and provides open-source code with benchmarking protocols in simulation and real-world settings. Our framework enables fair comparison, accelerates research, and is validated by successfully transferring simulated attacks to a physical LiDAR system. Beyond the framework, we offer insights into factors influencing attack success and advance understanding of adversarial robustness in real-world LiDAR perception.