FAAG: Fast Adversarial Audio Generation through Interactive Attack Optimisation

Automatic Speech Recognition services (ASRs) inherit deep neural networks' vulnerabilities like crafted adversarial examples. Existing methods often suffer from low efficiency because the target phases are added to the entire audio sample, resulting in high demand for computational resources. T...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Miao, Yuantian, Chen, Chao, Pan, Lei, Zhang, Jun, Xiang, Yang
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Cryptography and Security Computer Science - Sound
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!