发现紧急车辆灯光会干扰自动驾驶感知，导致误判或漏检。
PaniCar: Securing the Perception of Advanced Driving Assistance Systems Against Emergency Vehicle Lighting
- 提出新漏洞PaniCar：紧急车灯引发检测置信度波动，低于识别阈值。
- 测试7款商用系统，发现80%在强光下无法稳定识别车辆，置信度下降超0.3。
- 设计实时防护框架Caracetamol，提升检测稳定性，支持30-50帧/秒处理。
近年来，自动驾驶汽车安全问题备受关注，尤其在16起特斯拉（启用自动辅助驾驶）撞上静止应急车辆（警车、救护车、消防车）的事件后更为突出。现有研究指出强光源常在图像中引入耀斑伪影，降低图像质量，但其对目标检测性能的影响尚不明确。本研究揭示了一种名为PaniCar的数字现象：当激活应急车辆灯光时，物体检测器的置信度会波动至检测阈值以下，导致自动驾驶系统无法识别附近物体。这一漏洞带来重大安全隐患，且可能被攻击者利用以破坏高级驾驶辅助系统（ADAS）。我们评估了七款商用ADAS（Tesla Model 3、制造商C、HP、Pelsee、AZDOME、Imagebon、Rexing）、四种目标检测器（YOLO、SSD、RetinaNet、Faster R-CNN）及14种应急车辆灯光模式，分析技术与环境因素影响。同时评估四种主流耀斑去除方法，发现其性能与延迟均不满足实时驾驶需求。为此，我们提出Caracetamol框架，增强检测器对应急车辆灯光的鲁棒性。实验表明，在YOLOv3和Faster R-CNN上，Caracetamol将平均置信度提升0.20，最低置信度提升0.33，波动范围缩小0.33；且可实现30-50帧/秒的处理速度，满足实时检测要求。
原文摘要 · Abstract (English)
The safety of autonomous cars has come under scrutiny in recent years, especially after 16 documented incidents involving Teslas (with autopilot engaged) crashing into parked emergency vehicles (police cars, ambulances, and firetrucks). While previous studies have revealed that strong light sources often introduce flare artifacts in the captured image, which degrade the image quality, the impact of flare on object detection performance remains unclear. In this research, we unveil PaniCar, a digital phenomenon that causes an object detector's confidence score to fluctuate below detection thresholds when exposed to activated emergency vehicle lighting. This vulnerability poses a significant safety risk, and can cause autonomous vehicles to fail to detect objects near emergency vehicles. In addition, this vulnerability could be exploited by adversaries to compromise the security of advanced driving assistance systems (ADASs). We assess seven commercial ADASs (Tesla Model 3, "manufacturer C", HP, Pelsee, AZDOME, Imagebon, Rexing), four object detectors (YOLO, SSD, RetinaNet, Faster R-CNN), and 14 patterns of emergency vehicle lighting to understand the influence of various technical and environmental factors. We also evaluate four SOTA flare removal methods and show that their performance and latency are insufficient for real-time driving constraints. To mitigate this risk, we propose Caracetamol, a robust framework designed to enhance the resilience of object detectors against the effects of activated emergency vehicle lighting. Our evaluation shows that on YOLOv3 and Faster RCNN, Caracetamol improves the models' average confidence of car detection by 0.20, the lower confidence bound by 0.33, and reduces the fluctuation range by 0.33. In addition, Caracetamol is capable of processing frames at a rate of between 30-50 FPS, enabling real-time ADAS car detection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。