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...

Volledige beschrijving

Bewaard in:
Bibliografische gegevens
Hoofdauteurs: Binbin Liu, Jinlai Zhang, Jihong Zhu
Formaat: Artigo
Taal:Inglês
Gepubliceerd in: IEEE 2022-01-01
Reeks:IEEE Access
Onderwerpen:
3D adversarial attack
neural networks
point clouds
transferability
frequency
Online toegang:https://ieeexplore.ieee.org/document/9765977/
Tags: Voeg label toe
Geen labels, Wees de eerste die dit record labelt!

Gelijkaardige items