2022
DOI: 10.48550/arxiv.2201.10937
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Boosting 3D Adversarial Attacks with Attacking On Frequency

Abstract: Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks. Recently, 3D adversarial attacks, especially adversarial attacks on point clouds, have elicited mounting interest. However, adversarial point clouds obtained by previous methods show weak transferability and are easy to defend. To address these problems, in this paper we propose a novel point cloud attack (dubbed AOF) that pays more attention on the low-frequency component of point clouds. We combine the losses from point clou… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

0
1
0

Year Published

2022
2022
2022
2022

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 25 publications
0
1
0
Order By: Relevance
“…Only very recently, in 3D space, there is a parallel study [48] working on frequency domain in 3D adversarial attack methods. The work in [48] has suggested an adversarial attack based on the frequency domain when using DFT (graph-based). But our work proposes a defense method based on the frequency domain when using spherical harmonic transformation.…”
mentioning
confidence: 99%
“…Only very recently, in 3D space, there is a parallel study [48] working on frequency domain in 3D adversarial attack methods. The work in [48] has suggested an adversarial attack based on the frequency domain when using DFT (graph-based). But our work proposes a defense method based on the frequency domain when using spherical harmonic transformation.…”
mentioning
confidence: 99%