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...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Yang Gao, Xianrui Chang, Haoran Li, Jian Xu
Formato:	Artigo
Idioma:	Inglês
Publicado em:	Frontiers Media S.A. 2025-11-01
coleção:	Frontiers in Computer Science
Assuntos:	deep learning computer vision 3D point cloud adversarial attack security and privacy defense
Acesso em linha:	https://www.frontiersin.org/articles/10.3389/fcomp.2025.1626359/full
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!