Deep learning-based auto-driving systems are vulnerable to adversarial examples attacks which may result in wrong decision making and accidents. An adversarial example can fool the well trained neural networks by adding barely imperceptible perturbations to clean data. In this paper, we explore the mechanism of adversarial examples and adversarial robustness from the perspective of statistical mechanics, and propose an statistical mechanics-based interpretation model of adversarial robustness. The state transition caused by adversarial training based on the theory of fluctuation dissipation disequilibrium in statistical mechanics is formally constructed. Besides, we fully study the adversarial example attacks and training process on system robustness, including the influence of different training processes on network robustness. Our work is helpful to understand and explain the adversarial examples problems and improve the robustness of deep learning-based auto-driving systems.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Interpreting Adversarial Examples and Robustness for Deep Learning-Based Auto-Driving Systems


    Beteiligte:
    Wang, Ke (Autor:in) / Li, Fengjun (Autor:in) / Chen, Chien-Ming (Autor:in) / Hassan, Mohammad Mehedi (Autor:in) / Long, Jinyi (Autor:in) / Kumar, Neeraj (Autor:in)


    Erscheinungsdatum :

    01.07.2022


    Format / Umfang :

    1788880 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    CERTIFIED ADVERSARIAL ROBUSTNESS FOR DEEP REINFORCEMENT LEARNING

    LUETJENS BJOERN MALTE / EVERETT MICHAEL F / HOW JONATHAN P et al. | Europäisches Patentamt | 2021

    Freier Zugriff


    On Adversarial Robustness of Semantic Segmentation Models for Automated Driving

    Yin, Huilin / Wang, Ruining / Liu, Boyu et al. | IEEE | 2022


    Probabilistic Robustness Analysis: Examples

    Wojtkiewicz, Steven | AIAA | 2002


    Robustness of reinforcement learning based autonomous driving technologies

    Hart, Fabian / Technische Universität Dresden | SLUB | 2024