Categorical-Parallel Adversarial Defense for Perception Models on Single-Board Embedded Unmanned Vehicles
Significant advancements in robustness against input perturbations have been realized for deep neural networks (DNNs) through the application of adversarial training techniques. However, implementing these methods for perception tasks in unmanned vehicles, such as object detection and semantic segme...
Saved in:
| Main Authors: | Yilan Li, Xing Fan, Shiqi Sun, Yantao Lu, Ning Liu |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-08-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/8/9/438 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Adversarial attack and defense on graph neural networks: a survey
by: Jinyin CHEN, et al.
Published: (2021-06-01) -
Increasing the Robustness of Image Quality Assessment Models Through Adversarial Training
by: Anna Chistyakova, et al.
Published: (2024-11-01) -
Detection and Defense: Student-Teacher Network for Adversarial Robustness
by: Kyoungchan Park, et al.
Published: (2024-01-01) -
Randomized Purifier Based on Low Adversarial Transferability for Adversarial Defense
by: Sangjin Park, et al.
Published: (2024-01-01) -
CMDN: Pre-Trained Visual Representations Boost Adversarial Robustness for UAV Tracking
by: Ruilong Yu, et al.
Published: (2024-10-01)