On ℓ_p-norm Robustness of Ensemble Stumps and Trees

by   Yihan Wang, et al.

Recent papers have demonstrated that ensemble stumps and trees could be vulnerable to small input perturbations, so robustness verification and defense for those models have become an important research problem. However, due to the structure of decision trees, where each node makes decision purely based on one feature value, all the previous works only consider the ℓ_∞ norm perturbation. To study robustness with respect to a general ℓ_p norm perturbation, one has to consider the correlation between perturbations on different features, which has not been handled by previous algorithms. In this paper, we study the problem of robustness verification and certified defense with respect to general ℓ_p norm perturbations for ensemble decision stumps and trees. For robustness verification of ensemble stumps, we prove that complete verification is NP-complete for p∈(0, ∞) while polynomial time algorithms exist for p=0 or ∞. For p∈(0, ∞) we develop an efficient dynamic programming based algorithm for sound verification of ensemble stumps. For ensemble trees, we generalize the previous multi-level robustness verification algorithm to ℓ_p norm. We demonstrate the first certified defense method for training ensemble stumps and trees with respect to ℓ_p norm perturbations, and verify its effectiveness empirically on real datasets.


page 1

page 2

page 3

page 4


Robustness Verification of Tree-based Models

We study the robustness verification problem for tree-based models, incl...

Towards Verifying Robustness of Neural Networks Against Semantic Perturbations

Verifying robustness of neural networks given a specified threat model i...

Versatile Verification of Tree Ensembles

Machine learned models often must abide by certain requirements (e.g., f...

Connecting Interpretability and Robustness in Decision Trees through Separation

Recent research has recognized interpretability and robustness as essent...

Towards Certifying ℓ_∞ Robustness using Neural Networks with ℓ_∞-dist Neurons

It is well-known that standard neural networks, even with a high classif...

Automatic Perturbation Analysis on General Computational Graphs

Linear relaxation based perturbation analysis for neural networks, which...

A Stratified Approach to Robustness for Randomly Smoothed Classifiers

Strong theoretical guarantees of robustness can be given for ensembles o...