Trained Random Forests Completely Reveal your Dataset

arXiv:2402.19232v1 Announce Type: cross
Abstract: We introduce an optimization-based reconstruction attack capable of completely or near-completely reconstructing a dataset utilized for training a random forest. Notably, our approach relies solely on information readily available in commonly used libraries such as scikit-learn. To achieve this, we formulate the reconstruction problem as a combinatorial problem under a maximum likelihood objective. We demonstrate that this problem is NP-hard, though solvable at scale using constraint programming -- an approach rooted in constraint propagation and …

arxiv attack cs.cr cs.lg dataset forest forests information learn libraries near optimization problem random reveal training