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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Binbin Liu, Jinlai Zhang, Jihong Zhu
Format: Artigo
Sprache:Inglês
Veröffentlicht: IEEE 2022-01-01
Schriftenreihe:IEEE Access
Schlagworte:
3D adversarial attack
neural networks
point clouds
transferability
frequency
Online Zugang:https://ieeexplore.ieee.org/document/9765977/
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge