QR Code

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...

Full description

Saved in:
Main Authors: Yang Gao, Xianrui Chang, Haoran Li, Jian Xu
Format: Artigo
Language:Inglês
Published: Frontiers Media S.A. 2025-11-01
Series:Frontiers in Computer Science
Subjects:
deep learning
computer vision
3D point cloud
adversarial attack
security and privacy
defense
Online Access:https://www.frontiersin.org/articles/10.3389/fcomp.2025.1626359/full
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items