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...

Fuld beskrivelse

Na minha lista:
Bibliografiske detaljer
Main Authors: Binbin Liu, Jinlai Zhang, Jihong Zhu
Format: Artigo
Sprog:Inglês
Udgivet: IEEE 2022-01-01
Serier:IEEE Access
Fag:
3D adversarial attack
neural networks
point clouds
transferability
frequency
Online adgang:https://ieeexplore.ieee.org/document/9765977/
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!

Lignende værker