DeepManeuver: Adversarial Test Generation for Trajectory Manipulation of Autonomous Vehicles
DeepManeuver: Adversarial Test Generation for Trajectory Manipulation of Autonomous Vehicles
复制标题
DOI：
10.1109/tse.2023.3301443
复制
发表时间：
2023-10
影响因子：
7.4
通讯作者：
Meriel von Stein;David Shriver;Sebastian G. Elbaum
中科院分区：
文献类型：
--
作者：
Meriel von Stein;David Shriver;Sebastian G. Elbaum
对抗性测试生成技术旨在产生导致DNN计算错误输出的输入扰动。然而，对于由DNN驱动的自动驾驶车辆，这种扰动的影响被系统的其他部分衰减，并且随着车辆状态的演变而变得不那么有效。在这项工作中，我们认为，对抗性测试扰动对自动驾驶汽车有效，它们必须考虑DNN和车辆状态之间的微妙相互作用。基于这一见解，我们开发了DeepManeuver，这是一个自动化框架，将对抗性测试生成与车辆轨迹物理模拟相结合。因此，当运载工具沿着轨迹移动时，DeepManeuver使得能够细化候选扰动以：（1）考虑可能影响系统如何感知扰动的运载工具状态的变化;（2）保留扰动对先前状态的影响，使得当前状态仍然是可达的并且过去轨迹被保留;以及（3）导致需要满足车辆状态序列（例如，到达道路中的位置以导航急转弯）的多目标操纵。我们的评估表明，DeepManeuver可以产生扰动，以比最先进的技术更有效和一致地强制机动，平均提高20.7个百分点。我们还展示了DeepManeuver在扰乱车辆行为以实现多目标机动方面的有效性，成功率至少为52%。
Adversarial test generation techniques aim to produce input perturbations that cause a DNN to compute incorrect outputs. For autonomous vehicles driven by a DNN, however, the effect of such perturbations are attenuated by other parts of the system and are less effective as vehicle state evolves. In this work we argue that for adversarial testing perturbations to be effective on autonomous vehicles, they must account for the subtle interplay between the DNN and vehicle states. Building on that insight, we develop DeepManeuver, an automated framework that interleaves adversarial test generation with vehicle trajectory physics simulation. Thus, as the vehicle moves along a trajectory, DeepManeuver enables the refinement of candidate perturbations to: (1) account for changes in the state of the vehicle that may affect how the perturbation is perceived by the system; (2) retain the effect of the perturbation on previous states so that the current state is still reachable and past trajectory is preserved; and (3) result in multi-target maneuvers that require fulfillment of vehicle state sequences (e.g. reaching locations in a road to navigate a tight turn). Our assessment reveals that DeepManeuver can generate perturbations to force maneuvers more effectively and consistently than state-of-the-art techniques by 20.7 percentage points on average. We also show DeepManeuver's effectiveness at disrupting vehicle behavior to achieve multi-target maneuvers with a minimum 52% rate of success.