Advertisement

Combating Adversarial Inputs Using a Predictive-Estimator Network

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10635)

Abstract

Deep classification networks have shown great accuracy in classifying inputs. However, they fall prey to adversarial inputs, random inputs chosen to yield a classification with a high confidence. But perception is a two-way process, involving the interplay between feedforward sensory input and feedback expectations. In this paper, we construct a predictive estimator (PE) network, incorporating generative (predictive) feedback, and show that the PE network is less susceptible to adversarial inputs. We also demonstrate some other properties of the PE network.

Keywords

Neural network Predictive estimator Autoencoder Adversarial 

References

  1. 1.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105 (2012)Google Scholar
  2. 2.
    Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In: Computer Vision and Pattern Recognition, pp. 427–436 (2015)Google Scholar
  3. 3.
    Goodfellow, I., Pouget-Abadie, J., Mirza, M.: Generative adversarial networks. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)Google Scholar
  4. 4.
    Goodfellow, I., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: Proceedings of ICLR. arXiv:1412.6572v3 (2015)
  5. 5.
    Hinton, G.E.: A Practical guide to training restricted boltzmann machines. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 599–619. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-35289-8_32 CrossRefGoogle Scholar
  6. 6.
    Bastos, A.M., Usrey, W.M., Adams, R., Mangun, G.R., Fries, P., Friston, K.J.: Canonical Microcircuits for Predictive Coding. Neuron 76(4), 695–711 (2012)CrossRefGoogle Scholar
  7. 7.
    Rao, R.P.N., Ballard, D.H.: Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects. Nat. Neurosci. 2(1), 79–87 (1999)CrossRefGoogle Scholar
  8. 8.
    Le Cun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Handwritten digit recognition with a back-propagation network. In: Advances in Neural Information Processing Systems, pp. 396–404 (1990)Google Scholar
  9. 9.
    Luo, H., Fu, J., Glass, J.: Bidirectional Backpropagation: Towards Biologically Plausible Error Signal Transmission in Neural Networks. arXiv:1702.07097v3 (2017)

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Cheriton School of Computer ScienceUniversity of WaterlooWaterlooCanada

Personalised recommendations