Robustness Verification of Multi-Class Tree Ensembles
Laurens Devos, Lorenzo Cascioli, Jesse Davis
Abstract
Tree ensembles are one of the most widely used model classes. However, these models are susceptible to adversarial examples, which are slightly perturbed examples that elicit a misprediction. There has been significant research on designing approaches to verify the robustness of tree ensembles to such attacks. However, existing verification algorithms for tree ensembles are only able to analyze binary classifiers and hence address multiclass problems by reducing them to binary ones using a one-versus-other strategy. In this paper, we show that naively applying this strategy can yield incorrect results in certain situations. We address this shortcoming by proposing a novel approximate heuristic approach to verification for multiclass tree ensembles. Our approach is based on a novel generalization of the verification task, which we show emits other relevant verification queries.
BibTeX
@article{Devos_Cascioli_Davis_2024, title={Robustness Verification of Multi-Class Tree Ensembles}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30093}, DOI={10.1609/aaai.v38i19.30093}, abstractNote={Tree ensembles are one of the most widely used model classes. However, these models are susceptible to adversarial examples, which are slightly perturbed examples that elicit a misprediction.
There has been significant research on designing approaches to verify the robustness of tree ensembles to such attacks. However, existing verification algorithms for tree ensembles are only able to analyze binary classifiers and hence address multiclass problems by reducing them to binary ones using a one-versus-other strategy. In this paper, we show that naively applying this strategy can yield incorrect results in certain situations. We address this shortcoming by proposing a novel approximate heuristic approach to verification for multiclass tree ensembles. Our approach is based on a novel generalization of the verification task, which we show emits other relevant verification queries.}, number={19}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Devos, Laurens and Cascioli, Lorenzo and Davis, Jesse}, year={2024}, month={Mar.}, pages={21019-21028} }