Natural Occlusion-Based Backdoor Attacks: A Novel Approach to Compromising Pedestrian Detectors
Pedestrian detection systems are widely used in safety-critical domains such as autonomous driving, where deep neural networks accurately perceive individuals and distinguish them from other objects. However, their vulnerability to backdoor attacks remains understudied. Existing backdoor attacks, re...
Saved in:
| Main Authors: | Qiong Li, Yalun Wu, Qihuan Li, Xiaoshu Cui, Yuanwan Chen, Xiaolin Chang, Jiqiang Liu, Wenjia Niu |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/13/4203 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
FLARE: A Backdoor Attack to Federated Learning with Refined Evasion
by: Qingya Wang, et al.
Published: (2024-11-01) -
Backdoor defense method in federated learning based on contrastive training
by: Jiale ZHANG, et al.
Published: (2024-03-01) -
Stealthy graph backdoor attack based on feature trigger
by: Yang Chen, et al.
Published: (2025-06-01) -
Defending Deep Neural Networks Against Backdoor Attack by Using De-Trigger Autoencoder
by: Hyun Kwon
Published: (2025-01-01) -
A Backdoor Approach With Inverted Labels Using Dirty Label-Flipping Attacks
by: Orson Mengara
Published: (2025-01-01)