Self-driving cars (SDC) commonly implement the perception pipeline to detect the surrounding obstacles and track their moving trajectories, which lays the ground for the subsequent driving decision making process. Although the security of obstacle detection in SDC is intensively studied, not until very recently the attackers start to exploit the vulnerability of the tracking module. Compared with solely attacking the object detectors, this new attack strategy influences the driving decision more effectively with less attack budgets. However, little is known on whether the revealed vulnerability remains effective in end-to-end self-driving systems and, if so, how to mitigate the threat. In this paper, we present the first systematic research on the security of object tracking in SDC. Through a comprehensive case study on the full perception pipeline of a popular open-sourced self-driving system, Baidu's Apollo, we prove the mainstream multi-object tracker (MOT) based on Kalman Filter (KF) is unsafe even with an enabled multi-sensor fusion mechanism. Our root cause analysis reveals, the vulnerability is innate to the design of KF-based MOT, which shall error-handle the prediction results from the object detectors yet the adopted KF algorithm is prone to trust the observation more when its deviation from the prediction is larger. To address this design flaw, we propose a simple yet effective security patch for KF-based MOT, the core of which is an adaptive strategy to balance the focus of KF on observations and predictions according to the anomaly index of the observation-prediction deviation, and has certified effectiveness against a generalized hijacking attack model. Extensive evaluation on $4$ KF-based existing MOT implementations (including 2D and 3D, academic and Apollo ones) validate the defense effectiveness and the trivial performance overhead of our approach.
翻译:自驾驶汽车(SDC)通常使用感知管道来探测周围障碍并跟踪其移动轨迹,这为随后的驱动决策过程奠定了基础。虽然SDC对障碍探测的安全性进行了深入研究,但直到最近,攻击者才开始利用跟踪模块的脆弱性。与仅仅攻击物体探测器相比,这一新的攻击战略以较少攻击预算来更有效地影响驱动决定。然而,对于所暴露的脆弱性是否在最终至最终自我驱动系统中依然有效,以及如何减轻威胁,知之甚少。在本文件中,我们首次对SDC目标跟踪的安全性进行了系统研究。虽然SDC的阻力探测安全性安全性研究正在受到深入研究,但直到最近才开始利用目标探测器,与目标不同,与目标Kman过滤(KF)相比,主流多目标追踪器(MOT)更有效地影响着驱动决定。 我们的直观原因分析显示,基于KF的MOT的模型观测在设计上仍然很脆弱, 更精确地显示KOT的精确性观测结果,而我们从简单的K-F的精确度战略执行轨道到简单的K-Revil的精确度分析,而我们从一个简单的K-Revil的精确的精确的精确的精确度战略, 也是从一个简单的K-SD的测测测测算的轨道到一个简单的的轨道。