Exposing the Achilles’ heel of textual hate speech classifiers using indistinguishable adversarial examples

The accessibility of online hate speech has increased significantly, making it crucial for social-media companies to prioritize efforts to curb its spread. Although deep learning models demonstrate vulnerability to adversarial attacks, whether models fine-tuned for hate speech detection exhibit simi...

Celý popis

Podrobná bibliografie

Vydáno v:	Expert systems with applications Ročník 254; s. 124278
Hlavní autoři:	Aggarwal, Sajal, Vishwakarma, Dinesh Kumar
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 15.11.2024
Témata:	Adversarial attack Glyphs Hate speech Natural Language Processing (NLP) Offensive language Transformers Transformers Adversarial attack Glyphs Hate speech Offensive language Natural Language Processing (NLP)
ISSN:	0957-4174
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!