Dual-Key Multimodal Backdoors for Visual Question Answering

The success of deep learning has enabled advances in multimodal tasks that require non-trivial fusion of multiple input domains. Although multimodal models have shown potential in many problems, their increased complexity makes them more vulnerable to attacks. A Backdoor (or Trojan) attack is a clas...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-04
Hauptverfasser:	Walmer, Matthew, Sikka, Karan, Sur, Indranil, Shrivastava, Abhinav, Jha, Susmit
Format:	Artikel
Sprache:	eng
Schlagworte:	Complexity Feature extraction Optimization Questions Visual tasks
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!