Sensor Adversarial Traits: Analyzing Robustness of 3D Object Detection Sensor Fusion Models
This challenges the belief that additional sensors mitigate adversarial risks, with implications for safety in autonomous vehicles, though it is incremental as it builds on existing adversarial attack research.
The study analyzed the robustness of a high-performance sensor fusion model for 3D object detection in autonomous vehicles, finding it vulnerable to image-based adversarial attacks like disappearance, universal patch, and spoofing, despite using LIDAR data.
A critical aspect of autonomous vehicles (AVs) is the object detection stage, which is increasingly being performed with sensor fusion models: multimodal 3D object detection models which utilize both 2D RGB image data and 3D data from a LIDAR sensor as inputs. In this work, we perform the first study to analyze the robustness of a high-performance, open source sensor fusion model architecture towards adversarial attacks and challenge the popular belief that the use of additional sensors automatically mitigate the risk of adversarial attacks. We find that despite the use of a LIDAR sensor, the model is vulnerable to our purposefully crafted image-based adversarial attacks including disappearance, universal patch, and spoofing. After identifying the underlying reason, we explore some potential defenses and provide some recommendations for improved sensor fusion models.