Rethinking data augmentation for adversarial robustness
Authors:
- Hamid Eghbal-ZadehHEHamid Eghbal-Zadeh
- Werner ZellingerWZWerner Zellinger
- Maura PintorMPMaura Pintor
- Kathrin GrosseKGKathrin Grosse
- Khaled KoutiniKKKhaled Koutini
- Bernhard A. MoserBMBernhard A. Moser
- Battista BiggioBBBattista Biggio
- Gerhard WidmerGWGerhard Widmer
- 6 November 2023
- journal article
- research article
- Published by Elsevier in Information Sciences
- Vol. 654
Abstract
No abstract availableKeywords
Funding Information
- Fondazione di Sardegna (F73C22001320007, PE00000014)
- Ministero dell'istruzione dell'università e della ricerca
- Arbeiterkammer Oberösterreich
- Bundesministerium für Klimaschutz, Umwelt, Energie, Mobilität, Innovation und Technologie
- European Commission
- Österreichische Forschungsförderungsgesellschaft
- Bundesministerium für Digitalisierung und Wirtschaftsstandort
This publication has 5 references indexed in Scilit:
- Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothnessNeural Networks, 2020
- Robust Large Margin Deep Neural NetworksIEEE Transactions on Signal Processing, 2017
- Deep learningNature, 2015
- Robust domain adaptationAnnals of Mathematics and Artificial Intelligence, 2013
- On the mathematical foundations of learningBulletin of the American Mathematical Society, 2001