The reliability and robustness of 3D object detection play an instrumental role in the practical deployment of autonomous driving systems. Despite previous research indicating that adversarial examples can negatively affect 3D object detection models, leading to misinterpretations of the environment, these models still maintain the capability to detect the majority of objects within adversarially manipulated point clouds. To further probe into the adversarial robustness of these models, we propose an effective adversarial attack method named IoU-S attack in this paper. We meticulously formulate the adversarial loss to adversely affect the decision-making behavior (such as localization, etc.) of 3D object detection, thereby compromising its ability to accurately interpret the environment. Owing to the significant relevance of this adversarial loss to 3D object detection tasks, we have integrated the IoU-S attack into three attack paradigms: point cloud perturbation, detachment, and attachment. Comprehensive experiments on the widely accepted nuScenes dataset illustrate that the IoU-S attack outperforms existing attack methods in both white-box and black-box scenarios (https://github.com/haichen-ber/IoU-S-Attack). It reinforces its potential to serve as a valuable method in understanding and enhancing the robustness of 3D object detection models against adversarial attacks.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Efficient Adversarial Attack Strategy Against 3D Object Detection in Autonomous Driving Systems


    Beteiligte:
    Chen, Hai (Autor:in) / Yan, Huanqian (Autor:in) / Yang, Xiao (Autor:in) / Su, Hang (Autor:in) / Zhao, Shu (Autor:in) / Qian, Fulan (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.11.2024


    Format / Umfang :

    3483897 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Demo: Security of Camera-based Perception for Autonomous Driving under Adversarial Attack

    DiPalma, Christopher / Wang, Ningfei / Sato, Takami et al. | TIBKAT | 2021


    Lane changing scene automatic driving strategy and system considering adversarial attack

    REN YILONG / BAI XUESONG / YU HAIYANG et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Propulsion efficient autonomous driving strategy

    SOLIMAN IHAB | Europäisches Patentamt | 2020

    Freier Zugriff

    Overriding Autonomous Driving Systems Using Adaptive Adversarial Billboards

    Patel, Naman / Krishnamurthy, Prashanth / Garg, Siddharth et al. | IEEE | 2022