Boosting 3D Adversarial Attacks With Attacking on Frequency

Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks in the image domain. Recently, 3D adversarial attacks, especially adversarial attacks on point clouds, have elicited mounting interest. However, adversarial point clouds obtained by previous methods show weak transfe...

Полное описание

Сохранить в:
Библиографические подробности
Главные авторы: Binbin Liu, Jinlai Zhang, Jihong Zhu
Формат: Artigo
Язык:Inglês
Опубликовано: IEEE 2022-01-01
Серии:IEEE Access
Предметы:
3D adversarial attack
neural networks
point clouds
transferability
frequency
Online-ссылка:https://ieeexplore.ieee.org/document/9765977/
Метки: Добавить метку
Нет меток, Требуется 1-ая метка записи!

Схожие документы