2021
DOI: 10.1016/j.neucom.2021.06.078
|View full text |Cite
|
Sign up to set email alerts
|

High frequency patterns play a key role in the generation of adversarial examples

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
3
1

Relationship

1
8

Authors

Journals

citations
Cited by 13 publications
(5 citation statements)
references
References 9 publications
0
5
0
Order By: Relevance
“…Alternatively, the two issues might be addressed in a blended manner. For example, since adversarial perturbations have been shown to modify the frequencies of the resulting image spectrum [36], [37], an analysis in the frequency domain could be exploited for the detection of adversarial presentation attacks under the hypothesis that this frequency is kept along the PAI fabrication process.…”
Section: Black-box Resultsmentioning
confidence: 99%
“…Alternatively, the two issues might be addressed in a blended manner. For example, since adversarial perturbations have been shown to modify the frequencies of the resulting image spectrum [36], [37], an analysis in the frequency domain could be exploited for the detection of adversarial presentation attacks under the hypothesis that this frequency is kept along the PAI fabrication process.…”
Section: Black-box Resultsmentioning
confidence: 99%
“…Although great potentials and advantages the SNNs have held, their capabilities have not demonstrated as much as the ANNs, mainly because of the lack of the corresponding algorithms and the high-performance volatile memristors. [258,259] Therefore, multidisciplinary efforts to build an optimizing hardware platform to implement the SNNs, ANNs, and the hybrid ANNs-ANNs are necessary for an ultra-large-scale crossbar array-based system. In addition, the chip design is an important tache for the chip process.…”
Section: Challenges Progress and Opportunities For Volatile And Nonvo...mentioning
confidence: 99%
“…Most adversarial attack algorithms exploit CNNs' high frequency distortion vulnerability of convolutional neural networks [53]. Some research aimed at detecting the adversarial attacks is based on image spectrum analysis [54] [55].…”
Section: The Theoretical Approach To the Problem Solutionmentioning
confidence: 99%