Revisiting Physically Realizable Adversarial Object Attack against LiDAR-based Detection: Clarifying Problem Formulation and Experimental Protocols

TL;DR

This paper introduces a standardized, device-agnostic framework for physical adversarial object attacks on LiDAR-based detection, improving reproducibility, comparison, and understanding of attack transferability in real-world scenarios.

Contribution

The paper proposes a novel, open-source framework for physical adversarial attacks on LiDAR, addressing reproducibility issues and enabling fair benchmarking across different setups.

Findings

Successful transfer of simulated attacks to physical LiDAR systems.

Framework supports diverse attack methods and setups.

Provides insights into factors affecting attack success.

Abstract

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.