Perlin Noise Improve Adversarial Robustness

Adversarial examples are some special input that can perturb the output of a deep neural network, in order to make produce intentional errors in the learning algorithms in the production environment. Most of the present methods for generating adversarial examples require gradient information. Even u...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2021-12
Hauptverfasser:	Tang, Chengjun, Zhang, Kun, Xing, Chunfang, Ding, Yong, Xu, Zengmin
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Artificial neural networks Computer graphics Machine learning Neural networks Noise generation Perturbation Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!