OpBoost: A Vertical Federated Tree Boosting Framework Based on Order-Preserving Desensitization

Abstract

Vertical Federated Learning (FL) is a new paradigm that enables users with non-overlapping attributes of the same data samples to jointly train a model without directly sharing the raw data. Nevertheless, recent works show that it's still not sufficient to prevent privacy leakage from the training process or the trained model. This paper focuses on studying the privacy-preserving tree boosting algorithms under the vertical FL. The existing solutions based on cryptography involve heavy computation and communication overhead and are vulnerable to inference attacks. Although the solution based on Local Differential Privacy (LDP) addresses the above problems, it leads to the low accuracy of the trained model.This paper explores to improve the accuracy of the widely deployed tree boosting algorithms satisfying differential privacy under vertical FL. Specifically, we introduce a framework called Op-Boost. Three order-preserving desensitization algorithms satisfying a variant of LDP called distance-based LDP (dLDP) are designed to desensitize the training data. In particular, we optimize the dLDP definition and study efficient sampling distributions to further improve the accuracy and efficiency of the proposed algorithms. The proposed algorithms provide a trade-off between the privacy of pairs with large distance and the utility of desensitized values. Comprehensive evaluations show that OpBoost has a better performance on prediction accuracy of trained models compared with existing LDP approaches on reasonable settings. Our code is open source. 1

Decision Tree-Based Federated Learning: A Survey

“…FedXGBoost [54] uses LDP to add noise to perturb the first-order approximation, and calculates the split score through the perturbed results so as to accelerate the training process on the premise of small accuracy loss. OpBoost [58] desensitizes the training data using distance-based LDP (dLDP), and combines an effective sampling distribution to find the trade-off between desensitization values and privacy, thus improving the accuracy and efficiency of the original LDP model.…”