Abstract
The use of machine learning (ML) in airborne safety-critical systems requires new methods for certification, as the current standards and practices were defined and refined over decades with classical programming in mind and do not support this new development paradigm. This article provides an overview of the main challenges to the demonstration of compliance with regulation requirements raised by the use of ML and focuses on one particular case where the formal verification may become mandatory in future regulations, which is the verification of (partial) monotony properties. For this case, we propose a method to evaluate the monotony property using mixed integer linear programming. Contrary to the existing literature, our 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 for 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.
Similar content being viewed by others
References
Amershi, S., Begel, A., Bird, C., et al.: Software engineering for machine learning: a case study. In: 2019 IEEE/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP), pp. 291–300 (2019). https://doi.org/10.1109/ICSE-SEIP.2019.00042
Biannic, J., Hardier, G., Roos, C., et al.: Surrogate models for aircraft flight control: some off-line and embedded applications. Aerosp. Lab. 12, 1 (2016)
Carlini, N., Wagner, D.A.: Towards evaluating the robustness of neural networks. In: IEEE SP. IEEE Computer Society, pp. 39–57 (2017). https://doi.org/10.1109/SP.2017.49
Chen, S., Sun, Y., Li, D., et al.: Runtime safety assurance for learning-enabled control of autonomous driving vehicles. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 8978–8984 (2022). https://doi.org/10.1109/ICRA46639.2022.9812177
Cheng, C.H., Nührenberg, G., Ruess, H.: Maximum resilience of artificial neural networks. In: D’Souza, D., Narayan Kumar, K. (eds.) Automated Technology for Verification and Analysis, pp. 251–268. Springer, Berlin (2017). https://doi.org/10.1007/978-3-319-68167-2_18
Cofer, D.D., Amundson, I., Sattigeri, R., et al.: Run-time assurance for learning-enabled systems. In: Lee, R., Jha, S., Mavridou, A. (eds.) NASA Formal Methods – 12th International Symposium, NFM 2020, Moffett Field, CA, USA, May 11–15, 2020. Proceedings, Lecture Notes in Computer Science, vol. 12229, pp. 361–368. Springer, Berlin (2020). https://doi.org/10.1007/978-3-030-55754-6_21
Damour, M., Grancey, F.D., Gabreau, C., et al.: Towards certification of a reduced footprint ACAS-Xu system: a hybrid L-based solution. In: Proceedings, Computer Safety, Reliability, and Security – 40th International Conference,SAFECOMP 2021, York, UK, September 8-10, 2021, pp. 34–48 (2021). https://doi.org/10.1007/978-3-030-83903-1_3
de Moura, L.M., Bjørner, N.S.: Z3: an efficient SMT solver. In: Ramakrishnan, C.R., Rehof, J. (eds.) Tools and Algorithms for the Construction and Analysis of Systems, 14th International Conference, TACAS 2008, Held as Part of the Joint European Conferences on Theory and Practice of Software, ETAPS 2008. Budapest, Hungary, March 29-April 6, 2008. Proceedings, Lecture Notes in Computer Science, vol. 4963, pp. 337–340. Springer, Berlin (2008). https://doi.org/10.1007/978-3-540-78800-3_24
EASA: CS-25 Amendment 27 (2021). https://www.easa.Europa.eu/downloads/136622/en
EASA: EASA Concept Paper: First usable guidance for Level 1 machine learning applications (2021). https://www.easa.Europa.eu/downloads/134357/en
Feelders, A.J.: Prior knowledge in economic applications of data mining. In: European Conference on Principles of Data Mining and Knowledge Discovery, pp. 395–400. Springer, Berlin (2000). https://doi.org/10.1007/3-540-45372-5_42
Gauffriau, A., Malgouyres, F., Ducoffe, M.: Overestimation learning with guarantees (2021). arXiv preprint arXiv:2101.11717
Grossmann, I.E.: Review of nonlinear mixed-integer and disjunctive programming techniques. Optim. Eng. (2002)
Gupta, A., Shukla, N., Marla, L., et al.: How to incorporate monotonicity in deep networks while preserving flexibility? (2019). arXiv preprint arXiv:1909.10662
Gurobi Optimization, LLC: Gurobi Optimizer Reference Manual (2022). https://www.gurobi.com
Hao, J., Ye, W., Jia, L., et al.: Building surrogate models for engineering problems by integrating limited simulation data and monotonic engineering knowledge. Adv. Eng. Inform. 49, 101342 (2021). https://doi.org/10.1016/j.aei.2021.101342
Jian, Z.D., Chang, H.J., Ts, H., et al.: 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). https://doi.org/10.5220/0006418100830092
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). https://doi.org/10.1145/112646.112684
Katz, G., Huang, D.A., Ibeling, D., et al.: The marabou framework for verification and analysis of deep neural networks. In: Dillig, I., Tasiran, S. (eds.) Computer Aided Verification, pp. 443–452. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-25540-4_26
Liu, X., Han, X., Zhang, N., et al.: Certified monotonic neural networks. Adv. Neural Inf. Process. Syst. 33, 15427–15438 (2020). https://proceedings.neurips.cc/paper/2020/hash/b139aeda1c2914e3b579aafd3ceeb1bd-Abstract.html
Madry, A., Makelov, A., Schmidt, L., et al.: Towards deep learning models resistant to adversarial attacks. In: ICLR. OpenReview.net (2018). https://openreview.net/forum?id=rJzIBfZAb
Mamalet, F., Jenn, E., Flandin, G., et al.: White Paper Machine Learning in Certified Systems (2021). https://hal.archives-ouvertes.fr/hal-03176080
Marques-Silva, J., Ignatiev, A.: Delivering trustworthy AI through formal XAI. In: Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Applications of Artificial Intelligence, IAAI 2022, The Twelveth Symposium on Educational Advances in Artificial Intelligence, EAAI 2022 Virtual Event, February 22 – March 1, 2022, pp. 12342–12350. AAAI Press, Menlo Park (2022). https://ojs.aaai.org/index.php/AAAI/article/view/21499
Martin, R.: Assured software – a journey and discussion (2017). https://www.his-2019.co.uk/session/cwe-cve-its-history-and-future
Müller, M.N., Makarchuk, G., Singh, G., et al.: PRIMA: general and precise neural network certification via scalable convex hull approximations. Proc. ACM Program. Lang. 6(POPL), 43 (2022). https://doi.org/10.1145/3498704
Nguyen, A., Martínez, M.R.: MonoNet: towards interpretable models by learning monotonic features (2019). arXiv preprint arXiv:1909.13611
Phillips, P.J., Hahn, C., Fontana, P., et al.: Four principles of explainable artificial intelligence (2021). https://doi.org/10.6028/NIST.IR.8312. https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=933399
Picard, S., Chapdelaine, C., Cappi, C., et al.: Ensuring dataset quality for machine learning certification. In: ISSRE, pp. 275–282 (2020). https://doi.org/10.1109/ISSREW51248.2020.00085
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). https://proceedings.neurips.cc/paper/2018/hash/29c0605a3bab4229e46723f89cf59d83-Abstract.html
Rushby, J.: The interpretation and evaluation of assurance cases. Tech. Rep., (2015) http://www.csl.sri.com/users/rushby/papers/sri-csl-15-1-assurance-cases.pdf
Schweiger, A., Annighoefer, B., Reich, M., et al.: Classification for avionics capabilities enabled by artificial intelligence. In: 2021 IEEE/AIAA 40th Digital Avionics Systems Conference (DASC), pp. 1–10 (2021). https://doi.org/10.1109/DASC52595.2021.9594364
Singh, G., Gehr, T., Püschel, M., et al.: Robustness certification with refinement. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=HJgeEh09KQ
Sudakov, O., Koroteev, D., Belozerov, B., et al.: Artificial neural network surrogate modeling of oil reservoir: a case study. In: International Symposium on Neural Networks, pp. 232–241. Springer, Berlin (2019). https://doi.org/10.1007/978-3-030-22808-8_24
Tjeng, V., Xiao, K.Y., Tedrake, R.: Evaluating robustness of neural networks with mixed integer programming. In: ICLR (2019). https://openreview.net/forum?id=HyGIdiRqtm
Tsuzuku, Y., Sato, I., Sugiyama, M.: Lipschitz-margin training: scalable certification of perturbation invariance for deep neural networks. In: NeurIPS, pp. 6542–6551 (2018). https://proceedings.neurips.cc/paper/2018/hash/485843481a7edacbfce101ecb1e4d2a8-Abstract.html
Urban, C., Miné, A.: A review of formal methods applied to machine learning (2021). arXiv preprint arXiv:2104.02466. https://arxiv.org/abs/2104.02466
Urban, C., Christakis, M., Wüstholz, V., et al.: Perfectly parallel fairness certification of neural networks. Proc. ACM Program. Lang. 4(OOPSLA), 185 (2020). https://doi.org/10.1145/3428253
Wang, S., Pei, K., Whitehouse, J., et al.: Formal security analysis of neural networks using symbolic intervals. In: 27th USENIX Security Symposium (USENIX Security, vol. 18, pp. 1599–1614. USENIX Association, Baltimore (2018). https://www.usenix.org/conference/usenixsecurity18/presentation/wang-shiqi
Wang, S., Zhang, H., Xu, K., 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). https://proceedings.neurips.cc/paper/2021/hash/fac7fead96dafceaf80c1daffeae82a4-Abstract.html
Weng, T., Zhang, H., Chen, H., et al.: Towards fast computation of certified robustness for relu networks. In: ICML. Proceedings of Machine Learning Research (2018). http://proceedings.mlr.press/v80/weng18a.html
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). https://doi.org/10.1109/TNNLS.2018.2808470
Xu, K., Shi, Z., Zhang, H., et al.: Automatic perturbation analysis for scalable certified robustness and beyond. In: NeurIPS, pp. 1129–1141 (2020). https://proceedings.neurips.cc/paper/2020/hash/0cbc5671ae26f67871cb914d81ef8fc1-Abstract.html
Zhang, H., Weng, T.W., Chen, P.Y., et al.: Efficient neural network robustness certification with general activation functions. In: Advances in Neural Information Processing Systems, pp. 4939–4948 (2018). https://proceedings.neurips.cc/paper/2018/hash/d04863f100d59b3eb688a11f95b0ae60-Abstract.html
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, pp. 5757–5764 (2019). https://doi.org/10.1609/aaai.v33i01.33015757
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
All authors contributed equally to this work.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ducoffe, M., Gabreau, C., Ober, I. et al. Certification of avionic software based on machine learning: the case for formal monotony analysis. Int J Softw Tools Technol Transfer 26, 189–205 (2024). https://doi.org/10.1007/s10009-024-00741-6
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10009-024-00741-6