Towards improving fast adversarial training in multi-exit network

DOI10.1016/J.NEUNET.2022.02.015MaRDI QIDQ6048752zbMATH OpenOpenAlexFDO

Authors Sihong Chen, Haojing Shen, Ran Wang, Xi-Zhao Wang

Publication date 13 October 2023

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2022.02.015

zbMATH Keywords

adversarial defenseadversarial robustnessfast adversarial trainingmulti-exit network

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Enhancing adversarial attack transferability with multi-scale feature attack
• Wavelet regularization benefits adversarial training
• A3T: accuracy aware adversarial training
• Lagrangian objective function leads to improved unforeseen attack generalization
• Adversarial defense via the data-dependent activation, total variation minimization, and adversarial training

Cites work

• Deep learning
• Manifold adversarial training for supervised and semi-supervised learning

This page was built for publication: Towards improving fast adversarial training in multi-exit network

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6048752)