Sensitive Information of Deep Learning Based Face Anti-spoofing Algorithms

  • Yukun Ma
  • Lifang WuEmail author
  • Meng Jian
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10996)


Face anti-spoofing based on deep learning achieved good accuracy recently. However, deep learning model has no explicit mathematical presentation. Therefore, it is not clear about how the model works effectively. In this paper, we estimate the regions in face image, which are sensitive in deep learning based anti-spoofing algorithms. We first generate the adversarial examples from two different gradient-based methods. Then we analyze the distribution of the gradient and perturbations on the adversarial examples. And next we obtain the sensitive regions and evaluate the contribution of these regions to classification performance. By analyzing the sensitive regions, it could be observed that the CNN based anti-spoofing algorithms are sensitive to rich detailed regions and illumination. These observations are helpful to design an effective face anti-spoofing algorithm.


Face anti-spoofing Sensitive regions Gradient Convolutional neural networks Adversarial example 


  1. 1.
    Boulkenafet, Z., Komulainen, J., Hadid, A.: Face spoofing detection using colour texture analysis. IEEE Trans. Inf. Forensics Secur. 11(8), 1818–1830 (2017)CrossRefGoogle Scholar
  2. 2.
    Maatta, J., Hadid, A., Pietikainen, M.: Face spoofing detection from single images using texture and local shape analysis. IET Biometrics 1(1), 3–10 (2012)CrossRefGoogle Scholar
  3. 3.
    Wu, L., Xu, Y., Jian, M., Cai, W., Yan, C., Ma, Y.: Motion analysis based cross-database voting for face spoofing detection. In: Zhou, J., et al. (eds.) CCBR 2017. LNCS, vol. 10568, pp. 528–536. Springer, Cham (2017). Scholar
  4. 4.
    Li, L., Feng, X., Boulkenafet, Z., et al.: An original face anti-spoofing approach using partial convolutional neural network. In: International Conference on Image Processing Theory TOOLS and Applications, pp. 1–6. IEEE (2017)Google Scholar
  5. 5.
    Lucena, O., Junior, A., Moia, V., Souza, R., Valle, E., Lotufo, R.: Transfer learning using convolutional neural networks for face anti-spoofing. In: Karray, F., Campilho, A., Cheriet, F. (eds.) ICIAR 2017. LNCS, vol. 10317, pp. 27–34. Springer, Cham (2017). Scholar
  6. 6.
    Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I.J., Fergus, R.: Intriguing properties of neural networks. In: ICLR, abs/1312.6199 (2014)Google Scholar
  7. 7.
    Yin, B., Wang, W., Wang, L.: Review of Deep Learning. J. Beijing Univ. Technol. 1, 48–59 (2015)zbMATHGoogle Scholar
  8. 8.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Readings Cogn. Sci. 323(6088), 399–421 (1988)CrossRefGoogle Scholar
  9. 9.
    Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: ICML, pp. 1–10 (2015)Google Scholar
  10. 10.
    Moosavidezfooli, S.M., Fawzi, A., Frossard, P.: DeepFool: a simple and accurate method to fool deep neural networks. Computer Vision and Pattern Recognition. IEEE, pp. 2574–2582 (2016)Google Scholar
  11. 11.
    Ma, Y., Wu, L., Jian, M., Liu, F., Yang, Z.: Approach to generate adversarial examples for face-spoofing detection. J. Softw.
  12. 12.
    Anjos, A., Marcel, S.: Counter-measures to photo attacks in face recognition: a public database and a baseline. In: International Joint Conference on Biometrics, pp. 1–7. IEEE (2011)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Faculty of Information TechnologyBeijing University of TechnologyBeijingChina

Personalised recommendations