Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine Translation

While neural machine translation (NMT) models achieve success in our daily lives, they show vulnerability to adversarial attacks. Despite being harmful, these attacks also offer benefits for interpreting and enhancing NMT models, thus drawing increased research attention. However, existing studies o...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-09
Hauptverfasser:	Xue, Yanni, Hao, Haojie, Wang, Jiakai, Sheng, Qiang, Renshuai Tao, Yu, Liang, Pu Feng, Liu, Xianglong
Format:	Artikel
Sprache:	eng
Schlagworte:	Human performance Large language models Machine translation Solution space
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!