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...
I tiakina i:
| Ngā kaituhi matua: | , , , |
|---|---|
| Hōputu: | Artigo |
| Reo: | Inglês |
| I whakaputaina: |
Frontiers Media S.A.
2025-11-01
|
| Rangatū: | Frontiers in Computer Science |
| Ngā marau: | |
| Urunga tuihono: | https://www.frontiersin.org/articles/10.3389/fcomp.2025.1626359/full |
| Ngā Tūtohu: |
Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!
|