Abstract
Recent advances in machine learning are now being considered for integration in safety-critical systems such as vehicles, medical equipment and critical infrastructure. However, organizations in these domains are currently unable to provide convincing arguments that systems integrating machine learning technologies are safe to operate in their intended environments.
In this paper, we present a formal verification method for tree ensembles that leverage an abstraction-refinement approach to counteract combinatorial explosion. We implemented the method as an extension to a tool named VoTE, and demonstrate its applicability by verifying the robustness against perturbations in random forests and gradient boosting machines in two case studies. Our abstraction-refinement based extension to VoTE improves the performance by several orders of magnitude, scaling to tree ensembles with up to 50 trees with depth 10, trained on high-dimensional data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
References
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Bruneau, M., et al.: A framework to quantitatively assess and enhance the seismic resilience of communities. Earthq. Spectra 19(4), 733–752 (2003)
Chen, H., Zhang, H., Boning, D., Hsieh, C.J.: Adversarial defense for tree-based models. In: Safe Machine Learning workshop at ICLR (2019)
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
Einziger, G., Goldstein, M., Sa’ar, Y., Segall, I.: Verifying robustness of gradient boosted models. In: AAAI Conference on Artificial Intelligence (2019)
Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 29, 1189–1232 (2001)
Irsoy, O., Yildiz, O.T., Alpaydin, E.: Soft decision trees. In: International Conference on Pattern Recognition (ICPR). IEEE (2012)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Liu, C., Arnon, T., Lazarus, C., Barrett, C., Kochenderfer, M.J.: Algorithms for verifying deep neural networks. arXiv preprint arXiv:1903.06758 (2019)
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A.V., Gulin, A.: Catboost: unbiased boosting with categorical features. In: Advances in Neural Information Processing Systems (NIPS) (2018)
Sato, N., Kuruma, H., Nakagawa, Y., Ogawa, H.: Formal verification of decision-tree ensemble model and detection of its violating-input-value ranges. arXiv preprint arXiv:1904.11753 (2019)
Törnblom, J., Nadjm-Tehrani, S.: Formal verification of input-output mappings of tree ensembles. arXiv preprint arXiv:1905.04194 (2019)
Wang, F., Wang, Q., Nie, F., Yu, W., Wang, R.: Efficient tree classifiers for large scale datasets. Neurocomputing 284, 70–79 (2018)
Acknowledgements
This work was partially supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Törnblom, J., Nadjm-Tehrani, S. (2019). An Abstraction-Refinement Approach to Formal Verification of Tree Ensembles. In: Romanovsky, A., Troubitsyna, E., Gashi, I., Schoitsch, E., Bitsch, F. (eds) Computer Safety, Reliability, and Security. SAFECOMP 2019. Lecture Notes in Computer Science(), vol 11699. Springer, Cham. https://doi.org/10.1007/978-3-030-26250-1_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-26250-1_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-26249-5
Online ISBN: 978-3-030-26250-1
eBook Packages: Computer ScienceComputer Science (R0)