Evaluating the Robustness of Defense Mechanisms based on AutoEncoder Reconstructions against Carlini-Wagner Adversarial Attacks
Proceedings of the Northern Lights Deep Learning Workshop · 2020
DOI: 10.7557/18.5173 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Northern Lights Deep Learning Workshop, 2020. Verfasst von Petru Hlihor und 2 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Adversarial Examples represent a serious problem affecting the security of machine learning systems. In this paper we focus on a defense mechanism based on reconstructing images before classification using an autoencoder. We experiment on several types of autoencoders and evaluate the impact of strategies such as injecting noise in the input during training and in the latent space at inference time.We tested the models on adversarial examples generated with the Carlini-Wagner attack, in a white-box scenario and on the stacked system composed by the autoencoder and the classifier.
Zitieren
APA
Hlihor, P., Volpi, R., & Malagò, L. (2020). Evaluating the Robustness of Defense Mechanisms based on AutoEncoder Reconstructions against Carlini-Wagner Adversarial Attacks. Proceedings of the Northern Lights Deep Learning Workshop. https://doi.org/10.7557/18.5173
Vancouver
Hlihor P, Volpi R, Malagò L. Evaluating the Robustness of Defense Mechanisms based on AutoEncoder Reconstructions against Carlini-Wagner Adversarial Attacks. Proceedings of the Northern Lights Deep Learning Workshop. 2020. doi:10.7557/18.5173
BibTeX
@article{Hlihor2020,
author = {Hlihor, Petru and Volpi, Riccardo and Malagò, Luigi},
title = {Evaluating the Robustness of Defense Mechanisms based on AutoEncoder Reconstructions against Carlini-Wagner Adversarial Attacks},
journal = {Proceedings of the Northern Lights Deep Learning Workshop},
year = {2020},
doi = {10.7557/18.5173}
}
EUVIMED