Text Select-Backdoor: Selective Backdoor Attack for Text Recognition Systems

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...

Full description

Bibliographic Details
Main Authors: Hyun Kwon, Jang-Woon Baek
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Deep neural network
text domain
machine-learning security
backdoor attack
Online Access:https://ieeexplore.ieee.org/document/10741518/

Internet

https://ieeexplore.ieee.org/document/10741518/

Similar Items