On the claim for the existence of "Adversarial examples" in deep learning neural networks
Date Issued
October 2014
Author(s)
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.