Skip to main content

Neuron Pairs in Binarized Neural Networks Robustness Verification via Integer Linear Programming

  • Conference paper
  • First Online:
Combinatorial Optimization (ISCO 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14594))

Included in the following conference series:

  • 384 Accesses

Abstract

In the context of classification, robustness verification of a neural network is the problem which consists in determining if small changes of inputs lead to a change of their assigned classes. We investigate such a problem on binarized neural networks via an integer linear programming perspective. We namely present a constraint generation framework based on disjunctive programming and complete descriptions of polytopes related to outputs of neuron pairs. We also introduce an alternative relying on specific families of facet defining inequalities. Preliminary experiments assess the performance of the latter approach against recent single neuron convexification results.

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

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /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

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Amir, G., Wu, H., Barrett, C., Katz, G.: An SMT-based approach for verifying binarized neural networks. In: Groote, J.F., Larsen, K.G. (eds.) TACAS 2021. LNCS, vol. 12652, pp. 203–222. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-72013-1_11

    Chapter  Google Scholar 

  2. Anderson, R., Huchette, J., Ma, W., Tjandraatmadja, C., Vielma, J.P.: Strong mixed-integer programming formulations for trained neural networks. Math. Program. 183, 3–39 (2020)

    Article  MathSciNet  Google Scholar 

  3. Bal, H., et al.: A medium-scale distributed system for computer science research: infrastructure for the long term. Computer 49(5), 54–63 (2016)

    Article  Google Scholar 

  4. Bunel, R., Turkaslan, I., Torr, P.H.S., Kohli, P., Mudigonda, P.K.: A unified view of piecewise linear neural network verification. In: Neural Information Processing Systems (2017)

    Google Scholar 

  5. Cheng, C., Nührenberg, G., Ruess, H.: Verification of binarized neural networks. CoRR abs/1710.03107 (2017). http://arxiv.org/abs/1710.03107

  6. Christof, T., Löbel, A.: Porta - polyhedron representation transformation algorithm. https://porta.zib.de/

  7. Deng, L.: The MNIST database of handwritten digit images for machine learning research. IEEE Signal Process. Mag. 29(6), 141–142 (2012)

    Article  Google Scholar 

  8. Goldberg, Y.: A primer on neural network models for natural language processing. J. Artif. Intell. Res. 57, 345–420 (2016)

    Article  MathSciNet  Google Scholar 

  9. Han, S., Gómez, A.: Single-neuron convexifications for binarized neural networks. University of Southern California (2021). https://optimization-online.org/?p=17148

  10. Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2(5), 359–366 (1989)

    Article  Google Scholar 

  11. Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks. In: Lee, D., Sugiyama, M., Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 29. Curran Associates, Inc. (2016)

    Google Scholar 

  12. Jia, K., Rinard, M.C.: Efficient exact verification of binarized neural networks. CoRR abs/2005.03597 (2020). https://arxiv.org/abs/2005.03597

  13. Katz, G., Barrett, C., Dill, D.L., Julian, K., Kochenderfer, M.J.: Reluplex: a calculus for reasoning about deep neural networks. Formal Methods Syst. Des. 60, 87–116 (2022). https://doi.org/10.1007/s10703-021-00363-7

    Article  Google Scholar 

  14. Khalil, E.B., Gupta, A., Dilkina, B.: Combinatorial attacks on binarized neural networks. In: International Conference on Learning Representations (ICLR) (2019)

    Google Scholar 

  15. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C., Bottou, L., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol. 25. Curran Associates, Inc. (2012)

    Google Scholar 

  16. Lin, W., et al.: Robustness verification of classification deep neural networks via linear programming. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11410–11419 (2019)

    Google Scholar 

  17. Liu, C., Arnon, T., Lazarus, C., Strong, C., Barrett, C., Kochenderfer, M.J.: Algorithms for Verifying Deep Neural Networks (2021)

    Google Scholar 

  18. Lyu, B., Huchette, J.: Verifying binarized neural networks: convex relaxations, mixed-integer programming, and consistency. https://bochuanbob.github.io/BNN_MIP.pdf

  19. Narodytska, N., Kasiviswanathan, S., Ryzhyk, L., Sagiv, M., Walsh, T.: Verifying properties of binarized deep neural networks. In: AAAI Conference on Artificial Intelligence (AAAI) (2018)

    Google Scholar 

  20. Narodytska, N., Zhang, H., Gupta, A., Walsh, T.: In search for a sat-friendly binarized neural network architecture. In: International Conference on Learning Representations (ICLR) (2020)

    Google Scholar 

  21. Szegedy, C., et al.: Intriguing properties of neural networks. In: International Conference on Learning Representations (ICLR) (2014)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to José Neto .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Lubczyk, D., Neto, J. (2024). Neuron Pairs in Binarized Neural Networks Robustness Verification via Integer Linear Programming. In: Basu, A., Mahjoub, A.R., Salazar González, J.J. (eds) Combinatorial Optimization. ISCO 2024. Lecture Notes in Computer Science, vol 14594. Springer, Cham. https://doi.org/10.1007/978-3-031-60924-4_23

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-60924-4_23

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-60923-7

  • Online ISBN: 978-3-031-60924-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics