Energy-Based Adversarial Example Detection for SAR Images
Adversarial examples (AEs) bring increasing concern on the security of deep-learning-based synthetic aperture radar (SAR) target recognition systems. SAR AEs with perturbation constrained to the vicinity of the target have been recently in the spotlight due to the physical realization prospects. How...
Main Authors: | Zhiwei Zhang, Xunzhang Gao, Shuowei Liu, Bowen Peng, Yufei Wang |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-10-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/14/20/5168 |
Similar Items
-
Adversarial Attack for SAR Target Recognition Based on UNet-Generative Adversarial Network
by: Chuan Du, et al.
Published: (2021-10-01) -
An Empirical Study of Fully Black-Box and Universal Adversarial Attack for SAR Target Recognition
by: Bowen Peng, et al.
Published: (2022-08-01) -
Adversarial Examples for CNN-Based SAR Image Classification: An Experience Study
by: Haifeng Li, et al.
Published: (2021-01-01) -
Detecting Audio Adversarial Examples in Automatic Speech Recognition Systems Using Decision Boundary Patterns
by: Wei Zong, et al.
Published: (2022-12-01) -
Adversarial Deception Against SAR Target Recognition Network
by: Fan Zhang, et al.
Published: (2022-01-01)