Multi-Targeted Textual Backdoor Attack: Model-Specific Misrecognition via Trigger Position and Word Choice

Multi-Targeted Textual Backdoor Attack: Model-Specific Misrecognition via Trigger Position and Word Choice

Deep neural networks excel in tasks like image recognition and natural language processing, but they are susceptible to backdoor attacks. These attacks involve training a target model with samples that include specific triggers, causing the model to misclassify these triggered samples while still co...

Full description

Saved in:
Bibliographic Details
Main Authors: Taehwa Lee, Soojin Lee, Hyun Kwon
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Text domain
BERT
natural language processing
backdoor attack
poisoning attack
Online Access:https://ieeexplore.ieee.org/document/10938796/
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://ieeexplore.ieee.org/document/10938796/

Similar Items