arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.26462cs.RO
收藏

DTP-Attack:一种基于决策的黑盒对抗攻击用于轨迹预测

DTP-Attack: A decision-based black-box adversarial attack on trajectory prediction

Tongji University(同济大学);Graz University of Technology(格拉茨技术大学);Virtual Vehicle Research(虚拟车辆研究院)

Jiaxiang Li, Jun Yan, Daniel Watzenig, Huilin Yin

AI总结:

本文提出DTP-Attack,一种针对轨迹预测系统的基于决策的黑盒对抗攻击方法,通过二进制决策输出实现高可控性和可靠性,有效提升攻击成功率并降低对模型内部信息的依赖。

摘要:

轨迹预测系统对于自动驾驶安全至关重要,但仍然容易受到对抗攻击的影响,导致灾难性交通行为误解。现有攻击方法需要白盒访问和梯度信息,并依赖刚性的物理约束,限制了实际应用。我们提出DTP-Attack,一种基于决策的黑盒对抗攻击框架,专门针对轨迹预测系统。我们的方法仅基于二进制决策输出,无需模型内部信息或梯度,使其在实际场景中更具实用性。DTP-Attack采用一种新颖的边界行走算法,在没有固定约束的情况下导航对抗区域,通过保持接近性来自然维持轨迹真实性。与现有方法不同,我们的方法支持意图误分类攻击和预测准确性退化。在nuScenes和Apolloscape数据集上对最先进模型(包括Trajectron++和Grip++)的广泛评估显示了优越的性能。DTP-Attack在意图误分类攻击中实现了41-81%的攻击成功率,扰动低于0.45米即可操控感知驾驶行为,并使预测误差增加1.9-4.2。我们的方法在各种场景中均优于现有黑盒方法,保持了高可控性和可靠性。这些结果揭示了当前轨迹预测系统的基本漏洞,突显了在安全关键的自动驾驶应用中需要强大防御的紧迫需求。

英文摘要:

Trajectory prediction systems are critical for autonomous vehicle safety, yet remain vulnerable to adversarial attacks that can cause catastrophic traffic behavior misinterpretations. Existing attack methods require white-box access with gradient information and rely on rigid physical constraints, limiting real-world applicability. We propose DTP-Attack, a decision-based black-box adversarial attack framework tailored for trajectory prediction systems. Our method operates exclusively on binary decision outputs without requiring model internals or gradients, making it practical for real-world scenarios. DTP-Attack employs a novel boundary walking algorithm that navigates adversarial regions without fixed constraints, naturally maintaining trajectory realism through proximity preservation. Unlike existing approaches, our method supports both intention misclassification attacks and prediction accuracy degradation. Extensive evaluation on nuScenes and Apolloscape datasets across state-of-the-art models including Trajectron++ and Grip++ demonstrates superior performance. DTP-Attack achieves 41 - 81% attack success rates for intention misclassification attacks that manipulate perceived driving maneuvers with perturbations below 0.45 m, and increases prediction errors by 1.9 - 4.2 for accuracy degradation. Our method consistently outperforms existing black-box approaches while maintaining high controllability and reliability across diverse scenarios. These results reveal fundamental vulnerabilities in current trajectory prediction systems, highlighting urgent needs for robust defenses in safety-critical autonomous driving applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑