Segments-aware universal adversarial perturbations purification on 3D point cloud classifiers

Introduction3D point cloud classifiers, while powerful for representing real-world objects and environments, are vulnerable to adversarial perturbations, particularly Universal Adversarial Perturbations (UAPs). These UAPs pose significant security threats due to their input-agnostic nature. Current...

Полное описание

Библиографические подробности

Главные авторы:	Yang Gao, Xianrui Chang, Haoran Li, Jian Xu
Формат:	Artigo
Язык:	Inglês
Опубликовано:	Frontiers Media S.A. 2025-11-01
Серии:	Frontiers in Computer Science
Предметы:	deep learning computer vision 3D point cloud adversarial attack security and privacy defense
Online-ссылка:	https://www.frontiersin.org/articles/10.3389/fcomp.2025.1626359/full
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!