论文标题
advdo：轨迹预测的现实对抗攻击
AdvDO: Realistic Adversarial Attacks for Trajectory Prediction
论文作者
论文摘要
轨迹预测对于自动驾驶汽车（AV）是必不可少的，以计划正确且安全的驾驶行为。尽管许多先前的作品旨在达到更高的预测准确性，但很少有人研究其方法的对抗性鲁棒性。为了弥合这一差距，我们建议研究数据驱动的轨迹预测系统的对抗性鲁棒性。我们设计了一个基于优化的对抗攻击框架，该框架利用精心设计的可区分动态模型来生成现实的对抗轨迹。从经验上讲，我们基于最先进的预测模型的对抗性鲁棒性，并表明我们的攻击使通用指标和计划感知指标的预测错误增加了50％以上和37％。我们还表明，我们的攻击可以导致AV在模拟中驶离道路或碰撞到其他车辆中。最后，我们演示了如何使用对抗训练计划来减轻对抗性攻击。
Trajectory prediction is essential for autonomous vehicles (AVs) to plan correct and safe driving behaviors. While many prior works aim to achieve higher prediction accuracy, few study the adversarial robustness of their methods. To bridge this gap, we propose to study the adversarial robustness of data-driven trajectory prediction systems. We devise an optimization-based adversarial attack framework that leverages a carefully-designed differentiable dynamic model to generate realistic adversarial trajectories. Empirically, we benchmark the adversarial robustness of state-of-the-art prediction models and show that our attack increases the prediction error for both general metrics and planning-aware metrics by more than 50% and 37%. We also show that our attack can lead an AV to drive off road or collide into other vehicles in simulation. Finally, we demonstrate how to mitigate the adversarial attacks using an adversarial training scheme.
