Interpolated Adversarial Training: Achieving Robust Neural Networks Without Sacrificing Too Much Accuracy
Loading...
Access rights
openAccess
acceptedVersion
URL
Journal Title
Journal ISSN
Volume Title
A4 Artikkeli konferenssijulkaisussa
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Date
2019
Department
Major/Subject
Mcode
Degree programme
Language
en
Pages
Series
AISec'19: Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security, pp. 95-103
Abstract
Adversarial robustness has become a central goal in deep learning, both in theory and in practice. However, successful methods to improve the adversarial robustness (such as adversarial training) greatly hurt generalization performance on the unperturbed data. This could have a major impact on how achieving adversarial robustness affects real world systems (i.e. many may opt to forego robustness if it can improve accuracy on the unperturbed data). We propose Interpolated Adversarial Training, which employs recently proposed interpolation based training methods in the framework of adversarial training. On CIFAR-10, adversarial training increases the standard test error (when there is no adversary) from 4.43% to 12.32%, whereas with our Interpolated adversarial training we retain adversarial robustness while achieving a standard test error of only 6.45%. With our technique, the relative increase in the standard error for the robust model is reduced from 178.1% to just 45.5%.Description
Keywords
Other note
Citation
Verma, V, Lamb, A, Kannala, J & Bengio, Y 2019, Interpolated Adversarial Training: Achieving Robust Neural Networks Without Sacrificing Too Much Accuracy . in AISec'19: Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security . ACM, pp. 95-103, ACM Workshop on Artificial Intelligence and Security, London, United Kingdom, 15/11/2019 . https://doi.org/10.1145/3338501.3357369