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...

Full description

Saved in:
Bibliographic Details
Main Authors: Binbin Liu, Jinlai Zhang, Jihong Zhu
Format: Artigo
Language:Inglês
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
3D adversarial attack
neural networks
point clouds
transferability
frequency
Online Access:https://ieeexplore.ieee.org/document/9765977/
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items