Robust Optimal Classification Trees Against Adversarial Examples. (arXiv:2109.03857v1 [cs.LG])

Decision trees are a popular choice of explainable model, but just like
neural networks, they suffer from adversarial examples. Existing algorithms for
fitting decision trees robust against adversarial examples are greedy
heuristics and lack approximation guarantees. In this paper we propose ROCT, a
collection of methods to train decision trees that are optimally robust against
user-specified attack models. We show that the min-max optimization problem
that arises in adversarial learning can be solved using a single minimization
formulation for decision trees with 0-1 loss. We propose such formulations in
Mixed-Integer Linear Programming and Maximum Satisfiability, which widely
available solvers can optimize. We also present a method that determines the
upper bound on adversarial accuracy for any model using bipartite matching. Our
experimental results demonstrate that the existing heuristics achieve close to
optimal scores while ROCT achieves state-of-the-art scores.



Related post