Implicit adversarial data augmentation and robustness with noise-based learning

DOI10.1016/J.NEUNET.2021.04.008MaRDI QIDQ6054939zbMATH OpenOpenAlexFDO

Authors Priyadarshini Panda, Kaushik Roy

Publication date 28 September 2023

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2021.04.008

zbMATH Keywords

adversarial robustnessdeep learningprincipal component analysis

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Artificial neural networks and deep learning (68T07)

Recommendations

• Robustifying models against adversarial attacks by Langevin dynamics
• Adversarial defense via the data-dependent activation, total variation minimization, and adversarial training
• Wavelet regularization benefits adversarial training
• Enhancing adversarial attack transferability with multi-scale feature attack
• Theoretical investigation of generalization bounds for adversarial learning of deep neural networks

Cited in

(5)

• Adversarial defense via the data-dependent activation, total variation minimization, and adversarial training
• Theoretical investigation of generalization bounds for adversarial learning of deep neural networks
• Enhancing adversarial attack transferability with multi-scale feature attack
• Wavelet regularization benefits adversarial training
• Robustifying models against adversarial attacks by Langevin dynamics

This page was built for publication: Implicit adversarial data augmentation and robustness with noise-based learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6054939)