Abstract
Continuous deep learning models, referred to as Neural Ordinary Differential Equations (Neural ODEs), have received considerable attention over the last several years. Despite their burgeoning impact, there is a lack of formal analysis techniques for these systems. In this paper, we consider a general class of neural ODEs with varying architectures and layers, and introduce a novel reachability framework that allows for the formal analysis of their behavior. The methods developed for the reachability analysis of neural ODEs are implemented in a new tool called NNVODE. Specifically, our work extends an existing neural network verification tool to support neural ODEs. We demonstrate the capabilities and efficacy of our methods through the analysis of a set of benchmarks that include neural ODEs used for classification, and in control and dynamical systems, including an evaluation of the efficacy and capabilities of our approach with respect to existing software tools within the continuous-time systems reachability literature, when it is possible to do so.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
- 2.
CORA manual: https://tumcps.github.io/CORA/data/Cora2021Manual.pdf.
- 3.
GoTube can be found at https://github.com/DatenVorsprung/GoTube.
- 4.
Flowstar version 2.1.0 is available at https://flowstar.org/.
- 5.
JuliaReach can be found at https://juliareach.github.io/.
- 6.
NNV Release: https://zenodo.org/record/6840545#.YtGlrzfMKUk.
- 7.
Adversarial perturbations are applied before normalization, pixel values z\(_p\) \(\in \) [0, 255].
References
Althoff, M.: An introduction to CORA 2015. In: Proceedings of the Workshop on Applied Verification for Continuous and Hybrid Systems (2015)
Althoff, M.: Reachability analysis of nonlinear systems using conservative polynomialization and non-convex sets. In: Proceedings of the 16th International Conference on Hybrid Systems: Computation and Control, HSCC 2013, pp. 173–182. Association for Computing Machinery, New York (2013). https://doi.org/10.1145/2461328.2461358
Bak, S.: nnenum: verification of ReLU neural networks with optimized abstraction refinement. In: Dutle, A., Moscato, M.M., Titolo, L., Muñoz, C.A., Perez, I. (eds.) NFM 2021. LNCS, vol. 12673, pp. 19–36. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-76384-8_2
Bak, S., Bogomolov, S., Duggirala, P.S., Gerlach, A.R., Potomkin, K.: Reachability of black-box nonlinear systems after Koopman operator linearization. In: Jungers, R.M., Ozay, N., Abate, A. (eds.) 7th IFAC Conference on Analysis and Design of Hybrid Systems, ADHS 2021, Brussels, Belgium, 7–9 July 2021 (2021). IFAC-PapersOnLine 54, 253–258. Elsevier. https://doi.org/10.1016/j.ifacol.2021.08.507
Bak, S., Duggirala, P.S.: Simulation-equivalent reachability of large linear systems with inputs. In: Majumdar, R., Kunčak, V. (eds.) CAV 2017. LNCS, vol. 10426, pp. 401–420. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-63387-9_20
Bogomolov, S., Forets, M., Frehse, G., Potomkin, K., Schilling, C.: JuliaReach: a toolbox for set-based reachability. In: Proceedings of the 22nd ACM International Conference on Hybrid Systems: Computation and Control, pp. 39–44 (2019)
Carrara, F., Caldelli, R., Falchi, F., Amato, G.: On the robustness to adversarial examples of neural ode image classifiers. In: 2019 IEEE International Workshop on Information Forensics and Security (WIFS), pp. 1–6 (2019). https://doi.org/10.1109/WIFS47025.2019.9035109
Chen, R.T.Q., Rubanova, Y., Bettencourt, J., Duvenaud, D.: Neural ordinary differential equations. In: Advances in Neural Information Processing Systems (2018)
Chen, X., Ábrahám, E., Sankaranarayanan, S.: Flow*: an analyzer for non-linear hybrid systems. In: Sharygina, N., Veith, H. (eds.) CAV 2013. LNCS, vol. 8044, pp. 258–263. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-39799-8_18
Doyen, L., Frehse, G., Pappas, G.J., Platzer, A.: Verification of hybrid systems. In: Clarke, E., Henzinger, T., Veith, H., Bloem, R. (eds.) Handbook of Model Checking, pp. 1047–1110. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-10575-8_30
Dupont, E., Doucet, A., Teh, Y.W.: Augmented neural ODEs. In: Wallach, H., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019)
Dutta, S., Chen, X., Sankaranarayanan, S.: Reachability analysis for neural feedback systems using regressive polynomial rule inference. In: Proceedings of the 22nd ACM International Conference on Hybrid Systems: Computation and Control, HSCC 2019, pp. 157–168. ACM, New York (2019). https://doi.org/10.1145/3302504.3311807
Ehlers, R.: Formal verification of piece-wise linear feed-forward neural networks. In: D’Souza, D., Narayan Kumar, K. (eds.) ATVA 2017. LNCS, vol. 10482, pp. 269–286. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68167-2_19. https://doi.org/10/gh25vg
Fan, J., Huang, C., Chen, X., Li, W., Zhu, Q.: ReachNN*: a tool for reachability analysis of neural-network controlled systems. In: Hung, D.V., Sokolsky, O. (eds.) ATVA 2020. LNCS, vol. 12302, pp. 537–542. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59152-6_30
Frehse, G., et al.: SpaceEx: scalable verification of hybrid systems. In: Gopalakrishnan, G., Qadeer, S. (eds.) CAV 2011. LNCS, vol. 6806, pp. 379–395. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-22110-1_30
Gholaminejad, A., Keutzer, K., Biros, G.: ANODE: unconditionally accurate memory-efficient gradients for neural ODEs. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-2019, pp. 730–736. International Joint Conferences on Artificial Intelligence Organization, July 2019. https://doi.org/10.24963/ijcai.2019/103
Goodfellow, I., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: International Conference on Learning Representations (2015)
Gruenbacher, S., Cyranka, J., Lechner, M., Islam, M.A., Smolka, S.A., Grosu, R.: Lagrangian reachtubes: the next generation (2020)
Gruenbacher, S., Hasani, R.M., Lechner, M., Cyranka, J., Smolka, S.A., Grosu, R.: On the verification of neural ODEs with stochastic guarantees. In: AAAI (2021)
Gruenbacher, S., et al.: GoTube: scalable stochastic verification of continuous-depth models. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 6755–6764 (2022)
Hao, K.: A radical new neural network design could overcome big challenges in AI, April 2020. https://www.technologyreview.com/2018/12/12/1739/a-radical-new-neural-network-design-could-overcome-big-challenges-in-ai/
Huang, C., Fan, J., Li, W., Chen, X., Zhu, Q.: ReachNN: reachability analysis of neural-network controlled systems. ACM Trans. Embed. Comput. Syst. 18(5s), 1–22 (2019)
Ivanov, R., Carpenter, T., Weimer, J., Alur, R., Pappas, G., Lee, I.: Verisig 2.0: verification of neural network controllers using Taylor model preconditioning. In: Silva, A., Leino, K.R.M. (eds.) CAV 2021. LNCS, vol. 12759, pp. 249–262. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-81685-8_11
Ivanov, R., Carpenter, T.J., Weimer, J., Alur, R., Pappas, G.J., Lee, I.: Case study: verifying the safety of an autonomous racing car with a neural network controller. Association for Computing Machinery, New York (2020)
Ivanov, R., Jothimurugan, K., Hsu, S., Vaidya, S., Alur, R., Bastani, O.: Compositional learning and verification of neural network controllers. ACM Trans. Embed. Comput. Syst. 20(5s), 1–26 (2021). https://doi.org/10.1145/3477023
Ivanov, R., Weimer, J., Alur, R., Pappas, G.J., Lee, I.: Verisig: verifying safety properties of hybrid systems with neural network controllers. In: Proceedings of the 22nd ACM International Conference on Hybrid Systems: Computation and Control, HSCC 2019, pp. 169–178. ACM, New York (2019). https://doi.org/10.1145/3302504.3311806
Johnson, T.T., et al.: ARCH-COMP21 category report: artificial intelligence and neural network control systems (AINNCS) for continuous and hybrid systems plants. In: Frehse, G., Althoff, M. (eds.) 8th International Workshop on Applied Verification of Continuous and Hybrid Systems (ARCH 2021). EPiC Series in Computing, vol. 80, pp. 90–119. EasyChair (2021). https://doi.org/10.29007/kfk9
Johnson, T.T., et al.: ARCH-COMP20 category report: artificial intelligence and neural network control systems (AINNCS) for continuous and hybrid systems plants. In: Frehse, G., Althoff, M. (eds.) ARCH 2020. 7th International Workshop on Applied Verification of Continuous and Hybrid Systems (ARCH 2020). EPiC Series in Computing, vol. 74, pp. 107–139. EasyChair (2020). https://doi.org/10.29007/9xgv
Katz, G., Barrett, C., Dill, D.L., Julian, K., Kochenderfer, M.J.: Reluplex: an efficient SMT solver for verifying deep neural networks. In: Majumdar, R., Kunčak, V. (eds.) CAV 2017. LNCS, vol. 10426, pp. 97–117. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-63387-9_5
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
Kidger, P., Morrill, J., Foster, J., Lyons, T.: Neural controlled differential equations for irregular time series. In: Advances in Neural Information Processing Systems (2020)
Li, D., Bak, S., Bogomolov, S.: Reachability analysis of nonlinear systems using hybridization and dynamics scaling. In: Bertrand, N., Jansen, N. (eds.) FORMATS 2020. LNCS, vol. 12288, pp. 265–282. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-57628-8_16
Liu, C., Arnon, T., Lazarus, C., Strong, C., Barrett, C., Kochenderfer, M.J.: Algorithms for verifying deep neural networks. Found. Trends Optim. 4(3–4), 244–404 (2021). https://doi.org/10.1561/2400000035
Lopez, D.M., Musau, P., Hamilton, N., Johnson, T.T.: Reachability analysis of a general class of neural ordinary differential equations (2022). https://doi.org/10.48550/ARXIV.2207.06531
Manzanas Lopez, D., et al.: ARCH-COMP19 category report: artificial intelligence and neural network control systems (AINNCS) for continuous and hybrid systems plants. In: Frehse, G., Althoff, M. (eds.) ARCH 2019. 6th International Workshop on Applied Verification of Continuous and Hybrid Systems. EPiC Series in Computing, vol. 61, pp. 103–119. EasyChair, April 2019. https://doi.org/10.29007/rgv8
Massaroli, S., Poli, M., Park, J., Yamashita, A., Asama, H.: Dissecting neural ODEs. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 3952–3963. Curran Associates, Inc. (2020)
Morrill, J., Salvi, C., Kidger, P., Foster, J., Lyons, T.: Neural rough differential equations for long time series (2021)
Musau, P., Johnson, T.T.: Continuous-time recurrent neural networks (CTRNNs) (benchmark proposal). In: 5th Applied Verification for Continuous and Hybrid Systems Workshop (ARCH), Oxford, UK, July 2018. https://doi.org/10.29007/6czp
Norcliffe, A., Bodnar, C., Day, B., Simidjievski, N., Lió, P.: On second order behaviour in augmented neural ODEs. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 5911–5921. Curran Associates, Inc. (2020)
Ruan, W., Huang, X., Kwiatkowska, M.: Reachability analysis of deep neural networks with provable guarantees. In: The 27th International Joint Conference on Artificial Intelligence (IJCAI 2018) (2018)
Rubanova, Y., Chen, R.T.Q., Duvenaud, D.K.: Latent ordinary differential equations for irregularly-sampled time series. In: Wallach, H., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019)
Singh, G., Gehr, T., Mirman, M., Püschel, M., Vechev, M.: Fast and effective robustness certification. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, NIPS 2018, Red Hook, NY, USA, pp. 10825–10836. Curran Associates Inc. (2018)
Tran, H.-D., Bak, S., Xiang, W., Johnson, T.T.: Verification of deep convolutional neural networks using ImageStars. In: Lahiri, S.K., Wang, C. (eds.) CAV 2020. LNCS, vol. 12224, pp. 18–42. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-53288-8_2
Tran, H.D., Cei, F., Lopez, D.M., Johnson, T.T., Koutsoukos, X.: Safety verification of cyber-physical systems with reinforcement learning control. In: ACM SIGBED International Conference on Embedded Software (EMSOFT 2019). ACM, October 2019
Tran, H.-D., et al.: Star-based reachability analysis of deep neural networks. In: ter Beek, M.H., McIver, A., Oliveira, J.N. (eds.) FM 2019. LNCS, vol. 11800, pp. 670–686. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30942-8_39
Tran, H.-D., et al.: NNV: the neural network verification tool for deep neural networks and learning-enabled cyber-physical systems. In: Lahiri, S.K., Wang, C. (eds.) CAV 2020. LNCS, vol. 12224, pp. 3–17. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-53288-8_1
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), pp. 1599–1614 (2018)
Yan, H., Du, J., Tan, V.Y.F., Feng, J.: On robustness of neural ordinary differential equations (2020)
Acknowledgements
The material presented in this paper is based upon work supported by the National Science Foundation (NSF) through grant numbers 1910017 and 2028001, the Defense Advanced Research Projects Agency (DARPA) under contract number FA8750-18-C-0089, and the Air Force Office of Scientific Research (AFOSR) under contract number FA9550-22-1-0019. Any opinions, findings, and conclusions or recommendations expressed in this paper are those of the authors and do not necessarily reflect the views of AFOSR, DARPA, or NSF.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Manzanas Lopez, D., Musau, P., Hamilton, N.P., Johnson, T.T. (2022). Reachability Analysis of a General Class of Neural Ordinary Differential Equations. In: Bogomolov, S., Parker, D. (eds) Formal Modeling and Analysis of Timed Systems. FORMATS 2022. Lecture Notes in Computer Science, vol 13465. Springer, Cham. https://doi.org/10.1007/978-3-031-15839-1_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-15839-1_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-15838-4
Online ISBN: 978-3-031-15839-1
eBook Packages: Computer ScienceComputer Science (R0)