Privacy-Preserving Tree-Based Inference with TFHE
Not on the map. Why?
Abstract (arXiv)
Privacy enhancing technologies (PETs) have been proposed as a way to protect the privacy of data while still allowing for data analysis. In this work, we focus on Fully Homomorphic Encryption (FHE), a powerful tool that allows for arbitrary computations to be performed on encrypted data. FHE has received lots of attention in the past few years and has reached realistic execution times and correctness. More precisely, we explain in this paper how we apply FHE to tree-based models and get state-of-the-art solutions over encrypted tabular data. We show that our method is applicable to a wide range of tree-based models, including decision trees, random forests, and gradient boosted trees, and has been implemented within the Concrete-ML library, which is open-source at https://github.com/zama-ai/concrete-ml. With a selected set of use-cases, we demonstrate that our FHE version is very close to the unprotected version in terms of accuracy.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 9 of its 38 references that are in the map. First posted on arXiv 13 Feb 2023.
Builds on
9 of 38 references.
References · 9
- 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
- 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
- 2019Towards Federated Learning at Scale: System Designcited by 832
- 2021Tabular Data: Deep Learning is Not All You Needcited by 535
- 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
- 2018Privacy Preserving Machine Learning: Threats and Solutionscited by 79
- 2020Privacy-Preserving XGBoost Inferencecited by 5
- 2019Non-Interactive Private Decision Tree Evaluationcited by 2
- 2020Cryptotree: fast and accurate predictions on encrypted structured datacited by 2
Built on by
Citing papers per year: 2023: 1.
1 paper.