Code-Bridged Classifier (CBC): A Low or Negative Overhead Defense for Making a CNN Classifier Robust Against Adversarial Attacks

dc.contributor.authorBehnia, Farnaz
dc.contributor.authorMirzaeian, Ali
dc.contributor.authorSabokrou, Mohammad
dc.contributor.authorManoj, Saj
dc.contributor.authorMohsenin, Tinoosh
dc.contributor.authorKhasawneh, Khaled N.
dc.contributor.authorZhao, Liang
dc.contributor.authorHomayoun, Houman
dc.contributor.authorSasan, Avesta
dc.date.accessioned2020-03-05T15:35:16Z
dc.date.available2020-03-05T15:35:16Z
dc.date.issued2020-01-16
dc.description.abstractIn this paper, we propose Code-Bridged Classifier (CBC), a framework for making a Convolutional Neural Network (CNNs) robust against adversarial attacks without increasing or even by decreasing the overall models' computational complexity. More specifically, we propose a stacked encoder-convolutional model, in which the input image is first encoded by the encoder module of a denoising auto-encoder, and then the resulting latent representation (without being decoded) is fed to a reduced complexity CNN for image classification. We illustrate that this network not only is more robust to adversarial examples but also has a significantly lower computational complexity when compared to the prior art defenses.en_US
dc.description.urihttps://arxiv.org/abs/2001.06099en_US
dc.format.extent6 pagesen_US
dc.genrejournal articles preprintsen_US
dc.identifierdoi:10.13016/m2s30g-xsvq
dc.identifier.citationBehnia, Farnaz; Mirzaeian, Ali; Sabokrou, Mohammad; Manoj, Saj; Mohsenin, Tinoosh; Khasawneh, Khaled N.; Zhao, Liang; Homayoun, Houman; Sasan, Avesta; Code-Bridged Classifier (CBC): A Low or Negative Overhead Defense for Making a CNN Classifier Robust Against Adversarial Attacks; Machine Learning (2020); https://arxiv.org/abs/2001.06099en_US
dc.identifier.urihttp://hdl.handle.net/11603/17487
dc.language.isoen_USen_US
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.relation.ispartofUMBC Faculty Collection
dc.rightsThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
dc.titleCode-Bridged Classifier (CBC): A Low or Negative Overhead Defense for Making a CNN Classifier Robust Against Adversarial Attacksen_US
dc.typeTexten_US

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
2001.06099.pdf
Size:
1.43 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.56 KB
Format:
Item-specific license agreed upon to submission
Description: