Leveraging Universal Adversarial Perturbation and Frequency Band Filters Against Face Recognition
Universal adversarial perturbation (UAP) exhibits universality as it is independent of specific images. Although previous investigations have shown that the classification of natural images is susceptible to universal adversarial attacks, the impact of UAP on face recognition has not been fully inve...
Saved in:
| Main Authors: | Limengnan Zhou, Bufan He, Xi Jin, Guangling Sun |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/12/20/3287 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Optimization of Communication Signal Adversarial Examples by Selectively Preserving Low-Frequency Components of Perturbations
by: Yi Zhang, et al.
Published: (2024-11-01) -
AdvFaceGAN: a face dual-identity impersonation attack method based on generative adversarial networks
by: Hong Huang, et al.
Published: (2025-06-01) -
Adversarial Attacks to Manipulate Target Localization of Object Detector
by: Kai Xu, et al.
Published: (2024-01-01) -
A comprehensive survey of deep face verification systems adversarial attacks and defense strategies
by: Sohair Kilany, et al.
Published: (2025-08-01) -
A Gradual Adversarial Training Method for Semantic Segmentation
by: Yinkai Zan, et al.
Published: (2024-11-01)