Adversarial Calibration Attack on Autonomous Vehicles

2026-08-28

AI Summary

本文提出了一种针对自动驾驶车辆在线校准的对抗性校准攻击方法（ACA），通过设计特定海报诱导传感器错误校准，从而影响从感知到规划控制的系统性能。

Abstract

Autonomous vehicles (AVs) rely on accurate camera-LiDAR calibration for multimodal sensor fusion. In practice, calibration can drift due to vibration, temperature variation, or minor sensor displacement, motivating online calibration algorithms that detect and correct misalignment at runtime while allowing the vehicle to continue operating without a factory visit. Existing AV attacks largely assume correct calibration. We instead identify online sensor calibration as a new attack plane. A corrupted calibration update can persist across subsequent fusion operations, causing system-wide errors that propagate from perception to planning and control. We present Adversarial Calibration Attack (ACA), the first physical attack against camera-LiDAR online calibration. Using a single adversarial poster, ACA first spoofs the miscalibration detector to trigger the calibration process and then steers the calibration estimator toward an incorrect transformation. A unified optimization jointly designs the poster's geometry and texture for both objectives. We evaluate ACA across benchmark datasets, simulation, and physical experiments. On benchmark datasets such as KITTI and nuScenes, ACA induces up to 33.9 degrees mean rotational calibration error, thereby severely degrading object detection. In the CARLA simulator, the attack causes a collision when the corrupted calibration is accepted in vulnerable scenarios crafted by the attacker. On a real Husky robot, a printed adversarial poster successfully reproduces the calibration error. These results demonstrate that online calibration is a practical and safety-critical attack surface for AVs.

Problem

• Adversarial Calibration Attack
• Autonomous Vehicles
• Online Calibration
• Sensor Fusion
• Safety-Critical

Innovation

• Adversarial Calibration Attack
• Online Sensor Calibration
• Autonomous Vehicles
• Physical Attack
• Sensor Fusion