Skip to main content
SpringerLink
Log in

Formal Monotony Analysis of Neural Networks with Mixed Inputs: An Asset for Certification

  • Conference paper
  • First Online:
Formal Methods for Industrial Critical Systems (FMICS 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13487))

  • 431 Accesses

Abstract

The use of ML technology to design safety-critical systems requires a complete understanding of the neural network’s properties. Among the relevant properties in an industrial context, the verification of partial monotony may become mandatory. This paper proposes a method to evaluate the monotony property using a Mixed Integer Linear Programming (MILP) solver. Contrary to the existing literature, this monotony analysis provides a lower and upper bound of the space volume where the property does not hold, that we denote “Non-Monotonic Space Coverage”. This work has several advantages: (i) our formulation of the monotony property works on discrete inputs, (ii) the iterative nature of our algorithm allows for refining the analysis as needed, and (iii) from an industrial point of view, the results of this evaluation are valuable to the aeronautical domain where it can support the certification demonstration. We applied this method to an avionic case study (braking distance estimation using a neural network) where the verification of the monotony property is of paramount interest from a safety perspective.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 59.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 79.99
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

Notes

  1. 1.

    Note that we simplify the crosshatched area’s shape in order to know the omega value for the explanation.

References

  1. Biannic, J., Hardier, G., Roos, C., Seren, C., Verdier, L.: Surrogate models for aircraft flight control: some off-line and embedded applications. Aerospace Lab (12), 1 (2016)

    Google Scholar 

  2. Carlini, N., Wagner, D.A.: Towards evaluating the robustness of neural networks. In: IEEE SP, pp. 39–57. IEEE Computer Society (2017)

    Google Scholar 

  3. Cheng, C.-H., Nührenberg, G., Ruess, H.: Maximum resilience of artificial neural networks. In: D’Souza, D., Narayan Kumar, K. (eds.) ATVA 2017. LNCS, vol. 10482, pp. 251–268. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68167-2_18

    Chapter  Google Scholar 

  4. Damour, M., et al.: Towards certification of a reduced footprint ACAS-Xu system: a hybrid ML-based solution. In: Habli, I., Sujan, M., Bitsch, F. (eds.) SAFECOMP 2021. LNCS, vol. 12852, pp. 34–48. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-83903-1_3

    Chapter  Google Scholar 

  5. EASA: Concept paper first usable guidance for level 1 machine learning applications (2021). https://www.easa.europa.eu/downloads/134357/en

  6. Feelders, A.J.: Prior knowledge in economic applications of data mining. In: Zighed, D.A., Komorowski, J., Żytkow, J. (eds.) PKDD 2000. LNCS (LNAI), vol. 1910, pp. 395–400. Springer, Heidelberg (2000). https://doi.org/10.1007/3-540-45372-5_42

    Chapter  Google Scholar 

  7. Gauffriau, A., Malgouyres, F., Ducoffe, M.: Overestimation learning with guarantees. arXiv preprint arXiv:2101.11717 (2021)

  8. Grossmann, I.E.: Review of nonlinear mixed-integer and disjunctive programming techniques. Optim. Eng. 3(3), 227–252 (2002)

    Article  MathSciNet  Google Scholar 

  9. Gupta, A., Shukla, N., Marla, L., Kolbeinsson, A., Yellepeddi, K.: How to incorporate monotonicity in deep networks while preserving flexibility? arXiv preprint arXiv:1909.10662 (2019)

  10. Gurobi Optimization, LLC: Gurobi Optimizer Reference Manual (2022). https://www.gurobi.com

  11. Hao, J., Ye, W., Jia, L., Wang, G., Allen, J.: Building surrogate models for engineering problems by integrating limited simulation data and monotonic engineering knowledge. Adv. Eng. Inform. 49, 101342 (2021)

    Article  Google Scholar 

  12. Jian, Z.D., Chang, H.J., Hsu, T.S., Wang, D.W.: Learning from simulated world - surrogates construction with deep neural network. In: SIMULTECH 2017: Proceedings of the 7th International Conference on Simulation and Modeling Methodologies, Technologies and Applications. SCITEPRESS (2017)

    Google Scholar 

  13. Karpf, J.: Inductive modelling in law: example based expert systems in administrative law. In: Proceedings of the 3rd International Conference on Artificial Intelligence and Law, pp. 297–306 (1991)

    Google Scholar 

  14. Katz, G., et al.: The marabou framework for verification and analysis of deep neural networks. In: Dillig, I., Tasiran, S. (eds.) CAV 2019. LNCS, vol. 11561, pp. 443–452. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-25540-4_26

    Chapter  Google Scholar 

  15. Liu, X., Han, X., Zhang, N., Liu, Q.: Certified monotonic neural networks. Adv. Neural. Inf. Process. Syst. 33, 15427–15438 (2020)

    Google Scholar 

  16. Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: ICLR. OpenReview.net (2018)

    Google Scholar 

  17. Mamalet, F., et al.: White paper machine learning in certified systems. IRT Saint Exupéry - ANITI (2021)

    Google Scholar 

  18. Müller, M.N., Makarchuk, G., Singh, G., Püschel, M., Vechev, M.: PRIMA: general and precise neural network certification via scalable convex hull approximations. Proc. ACM Program. Lang. 6(POPL), 1–33 (2022)

    Google Scholar 

  19. Nguyen, A.P., Martínez, M.R.: Mononet: towards interpretable models by learning monotonic features. arXiv preprint arXiv:1909.13611 (2019)

  20. Peterson, E., DeVore, M., Cooper, J., Carr, G.: Run time assurance as an alternate concept to contemporary development assurance processes. NASA/CR-2020-220586 (2020)

    Google Scholar 

  21. Raghunathan, A., Steinhardt, J., Liang, P.S.: Semidefinite relaxations for certifying robustness to adversarial examples. In: Advances in Neural Information Processing Systems, pp. 10877–10887 (2018)

    Google Scholar 

  22. Sudakov, O., Koroteev, D., Belozerov, B., Burnaev, E.: Artificial neural network surrogate modeling of oil reservoir: a case study. In: Lu, H., Tang, H., Wang, Z. (eds.) ISNN 2019. LNCS, vol. 11555, pp. 232–241. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-22808-8_24

    Chapter  Google Scholar 

  23. Tjeng, V., Xiao, K.Y., Tedrake, R.: Evaluating robustness of neural networks with mixed integer programming. In: ICLR (2019)

    Google Scholar 

  24. Tsuzuku, Y., Sato, I., Sugiyama, M.: Lipschitz-margin training: scalable certification of perturbation invariance for deep neural networks. In: NeurIPS, pp. 6542–6551 (2018)

    Google Scholar 

  25. Urban, C., Christakis, M., Wüstholz, V., Zhang, F.: Perfectly parallel fairness certification of neural networks. Proc. ACM Program. Lang. 4(OOPSLA), 1–30 (2020)

    Google Scholar 

  26. Urban, C., Miné, A.: A review of formal methods applied to machine learning. arXiv preprint arXiv:2104.02466 (2021)

  27. Wang, S., Pei, K., Whitehouse, J., Yang, J., Jana, S.: Formal security analysis of neural networks using symbolic intervals. In: 27th USENIX Security Symposium (USENIX Security 2018), Baltimore, MD, pp. 1599–1614. USENIX Association, August 2018

    Google Scholar 

  28. Wang, S., et al.: Beta-CROWN: efficient bound propagation with per-neuron split constraints for neural network robustness verification. In: Advances in Neural Information Processing Systems (2021)

    Google Scholar 

  29. Weng, T.W., et al.: Towards fast computation of certified robustness for ReLU networks. arXiv preprint arXiv:1804.09699 (2018)

  30. Xiang, W., Tran, H.D., Johnson, T.T.: Output reachable set estimation and verification for multilayer neural networks. IEEE Trans. Neural Netw. Learn. Syst. 29(11), 5777–5783 (2018)

    Article  MathSciNet  Google Scholar 

  31. Xu, K., et al.: Automatic perturbation analysis for scalable certified robustness and beyond. In: NeurIPS (2020)

    Google Scholar 

  32. Zhang, H., Weng, T.W., Chen, P.Y., Hsieh, C.J., Daniel, L.: Efficient neural network robustness certification with general activation functions. In: Advances in Neural Information Processing Systems, pp. 4939–4948 (2018)

    Google Scholar 

  33. Zhang, H., Zhang, P., Hsieh, C.J.: Recurjac: an efficient recursive algorithm for bounding jacobian matrix of neural networks and its applications. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 5757–5764 (2019)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Airbus Opération S.A.S, Toulouse, France

    Guillaume Vidot, Mélanie Ducoffe & Christophe Gabreau

  2. University of Toulouse, Institut de Recherche en Informatique de Toulouse, Toulouse, France

    Guillaume Vidot & Ileana Ober

  3. ISAE-SUPAERO, University of Toulouse, Toulouse, France

    Iulian Ober

Authors
  1. Guillaume Vidot
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mélanie Ducoffe
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Christophe Gabreau
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ileana Ober
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Iulian Ober
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Guillaume Vidot .

Editor information

Editors and Affiliations

  1. Eindhoven University of Technology, Eindhoven, The Netherlands

    Jan Friso Groote

  2. University of Twente, Enschede, The Netherlands

    Marieke Huisman

Rights and permissions

Reprints and permissions

Copyright information

© 2022 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

Vidot, G., Ducoffe, M., Gabreau, C., Ober, I., Ober, I. (2022). Formal Monotony Analysis of Neural Networks with Mixed Inputs: An Asset for Certification. In: Groote, J.F., Huisman, M. (eds) Formal Methods for Industrial Critical Systems. FMICS 2022. Lecture Notes in Computer Science, vol 13487. Springer, Cham. https://doi.org/10.1007/978-3-031-15008-1_3

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-15008-1_3

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-15007-4

  • Online ISBN: 978-3-031-15008-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation