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).
SYSTEMS AND METHODS FOR DEFENDING AGAINST PHYSICAL ATTACKS ON IMAGE CLASSIFICATION
2021-09-30
Patent
Electronic Resource
English
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 |
Systems and methods for defending against physical attacks on image classification
European Patent Office | 2025
|Defending Commercial Airliners against Missile Attacks
British Library Conference Proceedings | 2005
|Defending Transportation Networks against Random and Targeted Attacks
Transportation Research Record | 2011
|Defending Transportation Networks Against Random and Targeted Attacks
Online Contents | 2011
|METHOD, APPARATUS, DEVICE, AND STORAGE MEDIUM FOR DEFENDING AGAINST ATTACKS
European Patent Office | 2021
|