Boosted by the evolution of machine learning technology, large amount of data and advanced computing system, neural networks have achieved state-of-the-art performance that even exceeds human capability in many applications [1] [2] . However, adversarial attacks targeting neural networks have demonstrated detrimental impact in autonomous driving [3] . The adversarial attacks are capable of arbitrarily manipulating the neural network classification results with different input data which is non-perceivable to human.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    An Autoencoder Based Approach to Defend Against Adversarial Attacks for Autonomous Vehicles


    Contributors:
    Gan, Houchao (author) / Liu, Chen (author)


    Publication date :

    2020-02-01


    Size :

    170964 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    ICAS2016_0221: SECURE ESTIMATION FOR UNMANNED AERIAL VEHICLES AGAINST ADVERSARIAL ATTACKS

    Hu, Q. / Chang, Y. H. / Tomlin, C. J. | British Library Conference Proceedings | 2016


    ROBUST TRAJECTORY PREDICTIONS AGAINST ADVERSARIAL ATTACKS IN AUTONOMOUS MACHINES AND APPLICATIONS

    XIAO CHAOWEI / CAO YOLONG / XU DANFEI et al. | European Patent Office | 2024

    Free access

    Securing deep learning against adversarial attacks for connected and automated vehicles

    Zhao, Chunheng / Pisu, Pierluigi | TIBKAT | 2022

    Free access

    Toward Robust 3D Perception for Autonomous Vehicles: A Review of Adversarial Attacks and Countermeasures

    Yasas Mahima, K. T. / Perera, Asanka G. / Anavatti, Sreenatha et al. | IEEE | 2024