An Empirical Study of Fully Black-Box and Universal Adversarial Attack for SAR Target Recognition
It has been demonstrated that deep neural network (DNN)-based synthetic aperture radar (SAR) automatic target recognition (ATR) techniques are extremely susceptible to adversarial intrusions, that is, malicious SAR images including deliberately generated perturbations that are imperceptible to the h...
-д хадгалсан:
| Үндсэн зохиолчид: | , , , |
|---|---|
| Формат: | Artigo |
| Хэл сонгох: | Inglês |
| Хэвлэсэн: |
MDPI AG
2022-08-01
|
| Цуврал: | Remote Sensing |
| Нөхцлүүд: | |
| Онлайн хандалт: | https://www.mdpi.com/2072-4292/14/16/4017 |
| Шошгууд: |
Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!
|