Explainable Artificial Intelligence with Integrated Gradients for the Detection of Adversarial Attacks on Text Classifiers

Text classifiers are Artificial Intelligence (AI) models used to classify new documents or text vectors into predefined classes. They are typically built using supervised learning algorithms and labelled datasets. Text classifiers produce a predefined class as an output, which also makes them suscep...

Descripció completa

Dades bibliogràfiques

Autors principals:	Harsha Moraliyage, Geemini Kulawardana, Daswin De Silva, Zafar Issadeen, Milos Manic, Seiichiro Katsura
Format:	Artigo
Idioma:	Inglês
Publicat:	MDPI AG 2025-01-01
Col·lecció:	Applied System Innovation
Matèries:	adversarial attacks AI cybersecurity integrated gradients text classification explainable AI
Accés en línia:	https://www.mdpi.com/2571-5577/8/1/17
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!