Please use this identifier to cite or link to this item:
Title: On the claim for the existence of "Adversarial examples" in deep learning neural networks
Authors: Neocleous, Costas 
Schizas, Christos N. 
Keywords: Adversarial examples;Deep neural networks;Feature distribution in neural networks
Category: Computer and Information Sciences
Field: Natural Sciences
Issue Date: Oct-2014
Publisher: INSTICC Press
Source: 6th International Conference on Neural Computation Theory and Applications, NCTA 2014, Part of the 6th International Joint Conference on Computational Intelligence, IJCCI 2014; Rome; Italy; 22 October 2014 through 24 October 2014
Abstract: A recent article in which it is claimed that adversarial examples exist in deep artificial neural networks (ANN) is critically examined. The newly discovered properties of ANNs are critically evaluated. Specifically, we point that adversarial examples can be serious problems in critical applications of pattern recognition. Also, they may stall the further development of artificial neural networks. We challenge the absolute existence of these examples, as this has not been universally proven yet. We also suggest that ANN structures, that correctly recognize adversarial examples, can be developed.
ISBN: 978-989758054-3
Rights: © 2016 SCITEPRESS, Science and Technology Publications, Lda - All rights reserved.
Type: Conference Papers
Appears in Collections:Δημοσιεύσεις σε συνέδρια/Conference papers

Show full item record

Page view(s) 50

Last Week
Last month
checked on Dec 11, 2018

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.