Text Select-Backdoor: Selective Backdoor Attack for Text Recognition Systems
Deep neural networks exhibit excellent image, voice, text, and pattern recognition performance. However, they are vulnerable to adversarial and backdoor attacks. In a backdoor attack, the target model identifies input data unless it contains a specific trigger, at which point it mistakenly recognize...
Saved in:
| Main Authors: | Hyun Kwon, Jang-Woon Baek |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10741518/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
A Backdoor Attack Against LSTM-Based Text Classification Systems
by: Jiazhu Dai, et al.
Published: (2019-01-01) -
Multi-Targeted Textual Backdoor Attack: Model-Specific Misrecognition via Trigger Position and Word Choice
by: Taehwa Lee, et al.
Published: (2025-01-01) -
Backdoor Attack Based on Lossy Image Compression Using Discrete Cosine Transform
by: Yuting Liu, et al.
Published: (2024-01-01) -
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) -
Defending Deep Neural Networks Against Backdoor Attack by Using De-Trigger Autoencoder
by: Hyun Kwon
Published: (2025-01-01)