A Textual Backdoor Defense Method Based on Deep Feature Classification

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...

Full description

Bibliographic Details
Main Authors: Kun Shao, Junan Yang, Pengjiang Hu, Xiaoshuai Li
Format: Article
Language:English
Published: MDPI AG 2023-01-01
Series:Entropy
Subjects:
deep neural networks
natural language processing
adversarial machine learning
backdoor attacks
backdoor defenses
Online Access:https://www.mdpi.com/1099-4300/25/2/220

Internet

https://www.mdpi.com/1099-4300/25/2/220

Similar Items