Fixed Inter-Neuron Covariability Induces Adversarial Robustness

The vulnerability to adversarial perturbations is a major flaw of Deep Neural Networks (DNNs) that raises question about their reliability when in real-world scenarios. On the other hand, human perception, which DNNs are supposed to emulate, is highly robust to such perturbations, indicating that th...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-08
Hauptverfasser:	Muhammad Ahmed Shah, Bhiksha Raj
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Biological activity Machine learning Multilayer perceptrons Multilayers Neurons Perception Perturbation Robustness
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!