HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

Generating Natural Adversarial Hyperspectral examples with a modified Wasserstein GAN

Jean-Christophe Burnel 1 Kilian Fatras 1 Nicolas Courty 1
1 OBELIX - Environment observation with complex imagery
IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE, UBS - Université de Bretagne Sud
Abstract : Adversarial examples are a hot topic due to their abilities to fool a classifier's prediction. There are two strategies to create such examples, one uses the attacked classifier's gradients, while the other only requires access to the clas-sifier's prediction. This is particularly appealing when the classifier is not full known (black box model). In this paper, we present a new method which is able to generate natural adversarial examples from the true data following the second paradigm. Based on Generative Adversarial Networks (GANs) [5], it reweights the true data empirical distribution to encourage the classifier to generate ad-versarial examples. We provide a proof of concept of our method by generating adversarial hyperspectral signatures on a remote sensing dataset.
Document type :
Conference papers
Complete list of metadata

Cited literature [10 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02447625
Contributor : Jean-Christophe Burnel Connect in order to contact the contributor
Submitted on : Saturday, January 25, 2020 - 12:02:38 PM
Last modification on : Wednesday, November 3, 2021 - 6:05:58 AM

Files

main.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02447625, version 1
  • ARXIV : 2001.09993

Citation

Jean-Christophe Burnel, Kilian Fatras, Nicolas Courty. Generating Natural Adversarial Hyperspectral examples with a modified Wasserstein GAN. C&ESAR, Nov 2019, Rennes, France. ⟨hal-02447625⟩

Share

Metrics

Record views

147

Files downloads

54