ATRAS: Adversarially Trained Robust Architecture Search
In this paper, we explore the effect of architecture completeness on adversarial robustness. We train models with different architectures on CIFAR-10 and MNIST dataset. For each model, we vary different number of layers and different number of nodes in the layer. For every architecture candidate, we...
Gespeichert in:
Hauptverfasser: | , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | In this paper, we explore the effect of architecture completeness on
adversarial robustness. We train models with different architectures on
CIFAR-10 and MNIST dataset. For each model, we vary different number of layers
and different number of nodes in the layer. For every architecture candidate,
we use Fast Gradient Sign Method (FGSM) to generate untargeted adversarial
attacks and use adversarial training to defend against those attacks. For each
architecture candidate, we report pre-attack, post-attack and post-defense
accuracy for the model as well as the architecture parameters and the impact of
completeness to the model accuracies. |
---|---|
DOI: | 10.48550/arxiv.2106.06917 |