Towards Robust Speech Models: Mitigating Backdoor Attacks via Audio Signal Enhancement and Fine-Pruning Techniques
The widespread adoption of deep neural networks (DNNs) in speech recognition has introduced significant security vulnerabilities, particularly from backdoor attacks. These attacks allow adversaries to manipulate system behavior through hidden triggers while maintaining normal operation on clean inpu...
Saved in:
| Main Authors: | Heyan Sun, Qi Zhong, Minfeng Qi, Uno Fang, Guoyi Shi, Sanshuai Cui |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/6/984 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
A survey of backdoor attacks and defences: From deep neural networks to large language models
by: Ling-Xin Jin, et al.
Published: (2025-09-01) -
BDEKD: mitigating backdoor attacks in NLP models via ensemble knowledge distillation
by: Zijie Zhang, et al.
Published: (2025-07-01) -
A sparse and invisible targeted backdoor attack in federated learning
by: Qikun Zhang, et al.
Published: (2025-07-01) -
A Backdoor Approach With Inverted Labels Using Dirty Label-Flipping Attacks
by: Orson Mengara
Published: (2025-01-01) -
Stealthy graph backdoor attack based on feature trigger
by: Yang Chen, et al.
Published: (2025-06-01)