An image classification system defends against physically realizable attacks. A training dataset of input images is retrieved and an adversarial image is generated based on one of the input images that is selected. The adversarial image is created by occluding a portion of the selected image by superimposing a predetermined shape (e.g., a rectangle) containing noise on the selected image. A defense against occlusion attacks (DOA) classifier is trained using the training dataset and the adversarial image. The DOA classifier is utilized to classify captured images of items (e.g., street signs) that may have been attacked (e.g., sticker placement, vandalism).


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    SYSTEMS AND METHODS FOR DEFENDING AGAINST PHYSICAL ATTACKS ON IMAGE CLASSIFICATION


    Beteiligte:
    VOROBEYCHIK YEVGENIY (Autor:in) / WU TONG (Autor:in) / TONG LIANG (Autor:in)

    Erscheinungsdatum :

    2021-09-30


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Englisch


    Klassifikation :

    IPC:    B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06V




    Defending Transportation Networks against Random and Targeted Attacks

    Lou, Yingyan / Zhang, Lihui | Transportation Research Record | 2011


    METHOD, APPARATUS, DEVICE, AND STORAGE MEDIUM FOR DEFENDING AGAINST ATTACKS

    CUI ZHIYANG | Europäisches Patentamt | 2021

    Freier Zugriff

    AUTHENTICATION METHOD AND APPARATUS FOR DEFENDING AGAINST ATTACKS ON UAM AIRCRAFT

    MIN YOUNG BIN / PARK SEUNG WOOK | Europäisches Patentamt | 2024

    Freier Zugriff