Abstract
Machine learning has proved invaluable for a range of different tasks, yet it also proved vulnerable to evasion attacks, i.e., maliciously crafted perturbations of input data designed to force mispredictions. In this paper we propose a novel technique to verify the security of decision tree models against evasion attacks with respect to an expressive threat model, where the attacker can be represented by an arbitrary imperative program. Our approach exploits the interpretability property of decision trees to transform them into imperative programs, which are amenable for traditional program analysis techniques. By leveraging the abstract interpretation framework, we are able to soundly verify the security guarantees of decision tree models trained over publicly available datasets. Our experiments show that our technique is both precise and efficient, yielding only a minimal number of false positives and scaling up to cases which are intractable for a competitor approach.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Biggio, B., et al.: Evasion attacks against machine learning at test time. In: Blockeel, H., Kersting, K., Nijssen, S., Železný, F. (eds.) ECML PKDD 2013. LNCS (LNAI), vol. 8190, pp. 387–402. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40994-3_25
Biggio, B., Roli, F.: Wild patterns: ten years after the rise of adversarial machine learning. Pattern Recognit. 84, 317–331 (2018)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001). https://doi.org/10.1023/A:1010933404324
Breiman, L., Friedman, J.H., Olshen, R.A., Stone, C.J.: Classification and Regression Trees. Wadsworth, Belmont (1984)
Calzavara, S., Lucchese, C., Tolomei, G.: Adversarial training of gradient-boosted decision trees. In: Proceedings of CIKM. ACM (2019)
Calzavara, S., Lucchese, C., Tolomei, G., Abebe, S.A., Orlando, S.: Treant: training evasion-aware decision trees. Data Min. Knowl. Discov. (2020, to appear). https://doi.org/10.1007/s10618-020-00694-9
Chen, H., Zhang, H., Boning, D.S., Hsieh, C.: Robust decision trees against adversarial examples. In: Proceedings of ICML. PMLR (2019)
Chen, H., Zhang, H., Si, S., Li, Y., Boning, D.S., Hsieh, C.: Robustness verification of tree-based models. In: Proceedings of NeurIPS, pp. 12317–12328 (2019)
Cousot, P., Cousot, R.: Abstract interpretation: a unified lattice model for static analysis of programs by construction or approximation of fixpoints. In: Proceedings of POPL. ACM (1977)
Cousot, P., Cousot, R.: Systematic design of program analysis frameworks. In: Proceedings of POPL. ACM (1979)
Cousot, P., Halbwachs, N.: Automatic discovery of linear restraints among variables of a program. In: Proceedings of POPL. ACM Press (1978)
Dreossi, T., Jha, S., Seshia, S.A.: Semantic adversarial deep learning. In: Chockler, H., Weissenbacher, G. (eds.) CAV 2018. LNCS, vol. 10981, pp. 3–26. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-96145-3_1
Einziger, G., Goldstein, M., Sa’ar, Y., Segall, I.: Verifying robustness of gradient boosted models. In: Proceedings of AAAI, pp. 2446–2453. AAAI Press (2019)
Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 29, 1189–1232 (2001)
Gehr, T., Mirman, M., Drachsler-Cohen, D., Tsankov, P., Chaudhuri, S., Vechev, M.T.: AI2: safety and robustness certification of neural networks with abstract interpretation. In: Proceedings of Security and Privacy. IEEE Computer Society (2018)
Goodfellow, I., McDaniel, P., Papernot, N.: Making machine learning robust against adversarial inputs. Commun. ACM 61(7), 56–66 (2018)
Huang, X., Kwiatkowska, M., Wang, S., Wu, M.: Safety verification of deep neural networks. In: Majumdar, R., Kunčak, V. (eds.) CAV 2017. LNCS, vol. 10426, pp. 3–29. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-63387-9_1
Jeannet, B., Miné, A.: Apron: A library of numerical abstract domains for static analysis. In: Bouajjani, A., Maler, O. (eds.) CAV 2009. LNCS, vol. 5643, pp. 661–667. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-02658-4_52
Kantchelian, A., Tygar, J.D., Joseph, A.D.: Evasion and hardening of tree ensemble classifiers. In: Proceedings of ICML. JMLR.org (2016)
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
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: Proceedings of ICLR. OpenReview.net (2018)
Miné, A.: The octagon abstract domain. Higher-Order Symb. Comput. 19, 31–100 (2006). https://doi.org/10.1007/s10990-006-8609-1
Ranzato, F., Zanella, M.: Abstract interpretation of decision tree ensemble classifiers. In: Proceedings of AAAI. AAAI Press (2020)
Sadowski, C., Aftandilian, E., Eagle, A., Miller-Cushon, L., Jaspan, C.: Lessons from building static analysis tools at google. Commun. ACM 61(4), 58–66 (2018)
Szegedy, C., et al.: Intriguing properties of neural networks. In: Proceedings of ICLR (2014)
Törnblom, J., Nadjm-Tehrani, S.: An abstraction-refinement approach to formal verification of tree ensembles. In: Romanovsky, A., Troubitsyna, E., Gashi, I., Schoitsch, E., Bitsch, F. (eds.) SAFECOMP 2019. LNCS, vol. 11699, pp. 301–313. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-26250-1_24
Wang, S., Pei, K., Whitehouse, J., Yang, J., Jana, S.: Efficient formal safety analysis of neural networks. In: Proceedings of NeurIPS 2018 (2018)
Wang, S., Pei, K., Whitehouse, J., Yang, J., Jana, S.: Formal security analysis of neural networks using symbolic intervals. In: Proceedings of USENIX Security. USENIX Association (2018)
Xiang, W., et al.: Verification for machine learning, autonomy, and neural networks survey. CoRR abs/1810.01989 (2018). http://arxiv.org/abs/1810.01989
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Calzavara, S., Ferrara, P., Lucchese, C. (2020). Certifying Decision Trees Against Evasion Attacks by Program Analysis. In: Chen, L., Li, N., Liang, K., Schneider, S. (eds) Computer Security – ESORICS 2020. ESORICS 2020. Lecture Notes in Computer Science(), vol 12309. Springer, Cham. https://doi.org/10.1007/978-3-030-59013-0_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-59013-0_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59012-3
Online ISBN: 978-3-030-59013-0
eBook Packages: Computer ScienceComputer Science (R0)