Back to Search Start Over

Colored Noise Injection for Training Adversarially Robust Neural Networks

Authors :
Zheltonozhskii, Evgenii
Baskin, Chaim
Nemcovsky, Yaniv
Chmiel, Brian
Mendelson, Avi
Bronstein, Alex M.
Publication Year :
2020

Abstract

Even though deep learning has shown unmatched performance on various tasks, neural networks have been shown to be vulnerable to small adversarial perturbations of the input that lead to significant performance degradation. In this work we extend the idea of adding white Gaussian noise to the network weights and activations during adversarial training (PNI) to the injection of colored noise for defense against common white-box and black-box attacks. We show that our approach outperforms PNI and various previous approaches in terms of adversarial accuracy on CIFAR-10 and CIFAR-100 datasets. In addition, we provide an extensive ablation study of the proposed method justifying the chosen configurations.

Details

Language :
English
Database :
OpenAIRE
Accession number :
edsair.doi.dedup.....15ff69d04c9f03a65e3ab28e887d13eb