Trajectory prediction is critical for the safe planning and navigation of automated vehicles. The trajectory prediction models based on the neural networks are vulnerable to adversarial attacks. Previous attack methods have achieved high attack success rates but overlook the adaptability to realistic scenarios and the concealment of the deceits. To address this problem, we propose a speed-adaptive stealthy adversarial attack method named SA-Attack. This method searches the sensitive region of trajectory prediction models and generates the adversarial trajectories by using the vehicle-following method and incorporating information about forthcoming trajectories. Our method has the ability to adapt to different speed scenarios by reconstructing the trajectory from scratch. Fusing future trajectory trends and curvature constraints can guarantee the smoothness of adversarial trajectories, further ensuring the stealthiness of attacks. The empirical study on the datasets of nuScenes and Apolloscape demonstrates the attack performance of our proposed method. Finally, we also demonstrate the adaptability and stealthiness of SA-Attack for different speed scenarios. Our code is available at the repository: https://github.com/eclipse-bot/SA-Attack.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    SA-Attack: Speed-adaptive stealthy adversarial attack on trajectory prediction


    Contributors:
    Yin, Huilin (author) / Li, Jiaxiang (author) / Zhen, Pengju (author) / Yan, Jun (author)


    Publication date :

    2024-06-02


    Size :

    2213606 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    WeepingCAN: A Stealthy CAN Bus-off Attack

    Bloom, Gedare | TIBKAT | 2021


    Confiscating Flight Control System by Stealthy Output Injection Attack

    Dutta, Abhishek / Langbort, Cedric | AIAA | 2017


    From Weeping to Wailing: A Transitive Stealthy Bus-Off Attack

    Agbaje, Paul / Olufowobi, Habeeb / Hounsinou, Sena et al. | IEEE | 2024


    CASAD: CAN-Aware Stealthy-Attack Detection for In-Vehicle Networks

    Nowdehi, Nasser / Aoudi, Wissam / Almgren, Magnus et al. | ArXiv | 2019

    Free access