A Textual Backdoor Defense Method Based on Deep Feature Classification

Natural language processing (NLP) models based on deep neural networks (DNNs) are vulnerable to backdoor attacks. Existing backdoor defense methods have limited effectiveness and coverage scenarios. We propose a textual backdoor defense method based on deep feature classification. The method include...

Descripción completa

Detalles Bibliográficos
Autores principales: Shao, Kun, Yang, Junan, Hu, Pengjiang, Li, Xiaoshuai
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9955932/
https://www.ncbi.nlm.nih.gov/pubmed/36832587
http://dx.doi.org/10.3390/e25020220

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9955932/
https://www.ncbi.nlm.nih.gov/pubmed/36832587
http://dx.doi.org/10.3390/e25020220

Ejemplares similares