Evaluating and Enhancing the Robustness of Sustainable Neural Relationship Classifiers Using Query-Efficient Black-Box Adversarial Attacks

Evaluating and Enhancing the Robustness of Sustainable Neural Relationship Classifiers Using Query-Efficient Black-Box Adversarial Attacks

Neural relation extraction (NRE) models are the backbone of various machine learning tasks, including knowledge base enrichment, information extraction, and document summarization. Despite the vast popularity of these models, their vulnerabilities remain unknown; this is of high concern given their...

Full description

Bibliographic Details
Main Authors: Ijaz Ul Haq, Zahid Younas Khan, Arshad Ahmad, Bashir Hayat, Asif Khan, Ye-Eun Lee, Ki-Il Kim
Format: Article
Language:English
Published: MDPI AG 2021-05-01
Series:Sustainability
Subjects:
robust
sustainability
adversarial attack
black-box attack
TFIDF
relation extraction
Online Access:https://www.mdpi.com/2071-1050/13/11/5892

Internet

https://www.mdpi.com/2071-1050/13/11/5892

Similar Items