Robustness verification of tree-based models
Author(s)
Chen, Hongge; Zhang, Huan; Si, Si; Li, Yang; Boning, Duane S; Hsieh, Cho-Jui; ... Show more Show less
DownloadPublished version (678.7Kb)
Publisher Policy
Publisher Policy
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Terms of use
Metadata
Show full item recordAbstract
© 2019 Neural information processing systems foundation. All rights reserved. We study the robustness verification problem for tree based models, including decision trees, random forests (RFs) and gradient boosted decision trees (GBDTs). Formal robustness verification of decision tree ensembles involves finding the exact minimal adversarial perturbation or a guaranteed lower bound of it. Existing approaches find the minimal adversarial perturbation by a mixed integer linear programming (MILP) problem, which takes exponential time so is impractical for large ensembles. Although this verification problem is NP-complete in general, we give a more precise complexity characterization. We show that there is a simple linear time algorithm for verifying a single tree, and for tree ensembles the verification problem can be cast as a max-clique problem on a multi-partite graph with bounded boxicity. For low dimensional problems when boxicity can be viewed as constant, this reformulation leads to a polynomial time algorithm. For general problems, by exploiting the boxicity of the graph, we develop an efficient multi-level verification algorithm that can give tight lower bounds on robustness of decision tree ensembles, while allowing iterative improvement and any-time termination. On RF/GBDT models trained on 10 datasets, our algorithm is hundreds of times faster than a previous approach that requires solving MILPs, and is able to give tight robustness verification bounds on large GBDTs with hundreds of deep trees.
Date issued
2019Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer ScienceJournal
Advances in Neural Information Processing Systems