Skip to main content

Statistical Certification of Acceptable Robustness for Neural Networks

  • Conference paper
  • First Online:
Artificial Neural Networks and Machine Learning – ICANN 2021 (ICANN 2021)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 12891))

Included in the following conference series:

Abstract

Neural network robustness measurement is a critical step before deploying neural network applications. However, existing methods, such as neural network verification and validation, do not fully meet our criteria for robustness measurement. From the industrial point-of-view, this paper proposes to use statistical robustness certificates (SRC) for measuring the robustness of neural networks against random noises as well as semantic perturbations and tries to bridge between verification and validation methods through Hoeffding Inequality. Our experiments show that our method is accurate in comparing robustness of different neural networks and has polynomial time complexity which leads to 3x-30x boost in efficiency compared to related methods. Together with the intrinsic statistical guarantee, the issued certificates are considered practical in comparing the robustness of various commercial neural networks.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Bastani, O., Ioannou, Y., Lampropoulos, L., Vytiniotis, D., Nori, A., Criminisi, A.: Measuring neural net robustness with constraints. In: Advances in Neural Information Processing Systems, pp. 2613–2621 (2016)

    Google Scholar 

  2. Yu, F., Qin, Z., Liu, C., Zhao, L., Wang, Y., Chen, X.: Interpreting and evaluating neural network robustness (2019). arXiv preprint arXiv:1905.04270

  3. Hendrycks, D., Dietterich, T.: Benchmarking neural networks robustness to common corruptions and perturbations (2019). arXiv preprint arXiv:1903.12261

  4. Carlini N., Wagner, D.: Towards evaluating the robustness of neural networks. In: IEEE Symposium on Security and Privacy, pp. 39–57 (2017)

    Google Scholar 

  5. Szegedy, C., et al.: Intriguing properties of neural networks (2013). arXiv preprint arXiv:1312.6199

  6. Liu, C., Arnon, T., Lazarus, C., Barrett, C., Kochenderfer, M.J., Algorithms for verifying deep neural networks (2019). arXiv preprint arXiv:1903.06758

  7. Rauber, J., Brendel, W., Bethge, M.: Foolbox: a python toolbox to benchmark the robustness of machine learning models (2017). arXiv preprint arXiv:1707.04131

  8. Katz, G., Barrett, C., Dill, D.L., Julian, K., Kochenderfer, M.J.: Reluplex: an efficient SMT solver for verifying deep neural networks. In: International Conference on Computer Aided Verification, pp. 97–117 (2017)

    Google Scholar 

  9. Boopathy, A., Weng, T.W., Chen, P.Y., Liu, S., Daniel, L.: CNN-Cert: an efficient framework for certifying robustness of convolutional neural networks. Proc. AAAI Conf. Artif. Intell. 33, 3240–3247 (2019)

    Google Scholar 

  10. Singh, G., Gehr, T., Püschel, M., Vechev, M.: An abstract domain for certifying neural networks. Proc. ACM Program. Lang. 3, 1–30 (2019)

    Article  Google Scholar 

  11. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)

    Google Scholar 

  12. Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications (2017). arXiv preprint arXiv:1704.04861

  13. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  14. Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples (2014). arXiv preprint arXiv:1412.6572

  15. Singh, G., Gehr, T., Mirman, M., Püschel, M., Vechev, M.: Fast and effective robustness certification. In: Advances in Neural Information Processing Systems, pp. 10802–10813 (2018)

    Google Scholar 

  16. Dutta, S., Jha, S., Sanakaranarayanan, S., Tiwari, A.: Output range analysis for deep neural networks (2017). arXiv preprint arXiv:1709.09130

  17. Huang, X., Kwiatkowska, M., Wang, S., Wu, M.: Safety verification of deep neural networks. In: International Conference on Computer Aided Verification, pp. 3–29 (2017)

    Google Scholar 

  18. Papernot, N., et al.: Technical report on the cleverhans v2. 1.0 adversarial examples library (2016). arXiv preprint arXiv:1610.00768

  19. Baidu (2019).https://github.com/advboxes/perceptron-benchmark

  20. Narodytska, N., Kasiviswanathan, S.P.: Simple black-box adversarial perturbations for deep networks (2016). arXiv preprint arXiv:1612.06299

  21. Hoeffding, W.: Probability inequalities for sums of bounded random variables. J. Am. Stat. Assoc. 58, 13–30 (1963)

    Google Scholar 

  22. Serfling, R.: Probability inequalities for the sum in sampling without replacement. Ann. Stat. 38, 39–48 (1973)

    Google Scholar 

  23. Papernot, N., McDaniel, P., Wu, X., Jha, S., Swami, A.: Distillation as a defense to adversarial perturbations against deep neural networks. In: IEEE Symposium on Security and Privacy, pp. 582–597 (2016)

    Google Scholar 

  24. Mohapatra, J., Chen, P.Y., Liu, S., Daniel, L.: Towards verifying robustness of neural networks against semantic perturbations (2019). arXiv preprint arXiv:1912.09533

  25. FAA: System Safety Handbook, Washington, DC (2000)

    Google Scholar 

  26. https://github.com/MadryLab/mnist

  27. https://github.com/MadryLab/cifar10

  28. http://jaina.cs.ucdavis.edu/datasets/adv/imagenet/

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Chengqiang Huang .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Huang, C., Hu, Z., Huang, X., Pei, K. (2021). Statistical Certification of Acceptable Robustness for Neural Networks. In: Farkaš, I., Masulli, P., Otte, S., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2021. ICANN 2021. Lecture Notes in Computer Science(), vol 12891. Springer, Cham. https://doi.org/10.1007/978-3-030-86362-3_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-86362-3_7

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-86361-6

  • Online ISBN: 978-3-030-86362-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics