Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

preprint · arXiv (Cornell University) · 2018

Defending Against Adversarial Attacks by Leveraging an Entire GAN

Gokula Krishnan Santhanam, Paulina Grnarova

Cited by 42Open access

Abstract

Recent work has shown that state-of-the-art models are highly vulnerable to adversarial perturbations of the input. We propose cowboy, an approach to detecting and defending against adversarial attacks by using both the discriminator and generator of a GAN trained on the same dataset. We show that the discriminator consistently scores the adversarial samples lower than the real samples across multiple attacks and datasets. We provide empirical evidence that adversarial samples lie outside of the data manifold learned by the GAN. Based on this, we propose a cleaning method which uses both the discriminator and generator of the GAN to project the samples back onto the data manifold. This cleaning procedure is independent of the classifier and type of attack and thus can be deployed in existing systems.

Cite this paper

APA 7

Santhanam, G. K., & Grnarova, P. (2018). Defending Against Adversarial Attacks by Leveraging an Entire GAN. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1805.10652

MLA 9

Santhanam, Gokula Krishnan, and Paulina Grnarova. “Defending Against Adversarial Attacks by Leveraging an Entire GAN.” arXiv (Cornell University), 2018, https://doi.org/10.48550/arxiv.1805.10652.

Chicago

Santhanam, Gokula Krishnan, and Paulina Grnarova. 2018. “Defending Against Adversarial Attacks by Leveraging an Entire GAN.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1805.10652.

Harvard

Santhanam, G.K. and Grnarova, P. (2018) ‘Defending Against Adversarial Attacks by Leveraging an Entire GAN’, arXiv (Cornell University). Available at: https://doi.org/10.48550/arxiv.1805.10652.

BibTeX
@misc{santhanam2018defending,
  title = {{Defending Against Adversarial Attacks by Leveraging an Entire GAN}},
  author = {Santhanam, Gokula Krishnan and Grnarova, Paulina},
  journal = {arXiv (Cornell University)},
  year = {2018},
  doi = {10.48550/arxiv.1805.10652}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.

Related papers