On the Claim for the Existence of "Adversarial Examples" in Deep Learning Neural Networks
暂无分享,去创建一个
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.
[1] J. Gore,et al. Neural Correlates of the Attentional Blink , 2000, Neuron.
[2] Joan Bruna,et al. Intriguing properties of neural networks , 2013, ICLR.
[3] Kleanthis C. Neokleous,et al. A neural network model of the attentional blink phenomenon , 2009 .
[4] Yann LeCun,et al. The mnist database of handwritten digits , 2005 .
[5] Marvin Minsky,et al. Perceptrons: An Introduction to Computational Geometry , 1969 .