Autonomous driving safety based on LiDAR perception is increasingly becoming a hot spot. Specifically, 3D adversarial examples always make the prediction results of deep neural network models unpredictable, which poses a major security risk to autonomous driving systems. However, the vulnerability of 3D neural network models to adversarial examples is less explored. At present, existing adversarial attack methods often obtain 3D adversarial examples by perturbing the entire point cloud, which requires a large number of perturbed points, i.e. requires a large perturbation budget. In this paper, we propose a Salient Region Adversarial attack method (SR-Adv) to generate adversarial point clouds, by perturbing fewer regions and fewer points. To our knowledge, we are the first to propose region-based attacks for 3D point clouds. First, the proposed SR-Adv employs game theory to extract salient regions of point clouds. This mechanism assigns a value to each region to measure its importance to the 3D neural network model prediction results and realizes the vulnerability analysis of the 3D model. Second, we propose a novel optimization-based gradient attack algorithm to achieve adversarial attacks on salient regions. We evaluate the proposed SR-Adv attack method on the synthetic datasets ModelNet40 and ShapeNetPart as well as the real-world dataset KITTI and NuScenes. Experimental results show that the proposed SR-Adv achieves a state-of-the-art attack success rate and better imperceptibility by perturbing fewer points on 3D point clouds.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    SR-Adv: Salient Region Adversarial Attacks on 3D Point Clouds for Autonomous Driving


    Beteiligte:
    Zheng, Shijun (Autor:in) / Liu, Weiquan (Autor:in) / Guo, Yu (Autor:in) / Zang, Yu (Autor:in) / Shen, Siqi (Autor:in) / Wen, Chenglu (Autor:in) / Cheng, Ming (Autor:in) / Zhong, Ping (Autor:in) / Wang, Cheng (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.10.2024


    Format / Umfang :

    15816347 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Gradient-Free Adversarial Attacks on 3D Point Clouds from LiDAR Sensors

    Urfei, Jan / Smirnov, Fedor / Weichslgartner, Andreas et al. | Springer Verlag | 2023


    Adversarial Attacks Targeting Point-to-Point Wireless Networks

    Ghasemi, Ahmad / Moradikia, Majid / Zekavat, Seyed Reza et al. | IEEE | 2024


    Adversarial Driving: Attacking End-to-End Autonomous Driving

    Wu, Han / Yunas, Syed / Rowlands, Sareh et al. | IEEE | 2023


    GENERATING ADVERSARIAL DRIVING SCENARIOS FOR AUTONOMOUS VEHICLES

    PITTALUGA FRANCESCO / LIU BUYU / CHANDRAKER MANMOHAN et al. | Europäisches Patentamt | 2025

    Freier Zugriff

    GENERATING ADVERSARIAL DRIVING SCENARIOS FOR AUTONOMOUS VEHICLES

    PITTALUGA FRANCESCO / LIU BUYU / CHANDRAKER MANMOHAN et al. | Europäisches Patentamt | 2025

    Freier Zugriff