Model Mimic Attack: Knowledge Distillation for Provably Transferable Adversarial Examples

The vulnerability of artificial neural networks to adversarial perturbations in the black-box setting is widely studied in the literature. The majority of attack methods to construct these perturbations suffer from an impractically large number of queries required to find an adversarial example. In...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-10
Hauptverfasser:	Lukyanov, Kirill, Perminov, Andrew, Turdakov, Denis, Pautov, Mikhail
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Black boxes Knowledge management Perturbation
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!