Verifiable Boosted Tree Ensembles

arXiv:2402.14988v1 Announce Type: new
Abstract: Verifiable learning advocates for training machine learning models amenable to efficient security verification. Prior research demonstrated that specific classes of decision tree ensembles -- called large-spread ensembles -- allow for robustness verification in polynomial time against any norm-based attacker. This study expands prior work on verifiable learning from basic ensemble methods (i.e., hard majority voting) to advanced boosted tree ensembles, such as those trained using XGBoost or LightGBM. Our formal results indicate that robustness verification …

abstract arxiv basic cs.cr cs.lg cs.lo decision ensemble machine machine learning machine learning models norm polynomial prior research robustness security stat.ml study training tree type verification work