SilentWood: Private Inference Over Gradient-Boosting Decision Forests

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ko, Ronny, Kati, Abdelkarim, Geelen, Robin, Mahdavi, Rasoul Akhavan, Yoon, Byoungwoo, Shin, Jongho, Moroz, Igor, Jappinen, Anton, Lin, Zhiqiang, Onizuka, Makoto, Kerschbaum, Florian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911407682879488
author Ko, Ronny
Kati, Abdelkarim
Geelen, Robin
Mahdavi, Rasoul Akhavan
Yoon, Byoungwoo
Shin, Jongho
Moroz, Igor
Jappinen, Anton
Lin, Zhiqiang
Onizuka, Makoto
Kerschbaum, Florian
author_facet Ko, Ronny
Kati, Abdelkarim
Geelen, Robin
Mahdavi, Rasoul Akhavan
Yoon, Byoungwoo
Shin, Jongho
Moroz, Igor
Jappinen, Anton
Lin, Zhiqiang
Onizuka, Makoto
Kerschbaum, Florian
contents Gradient boosting decision forests, used by XGBoost or AdaBoost, offer higher accuracy and lower training times than decision trees for large datasets. Protocols for private inference over decision trees can be used to preserve the privacy of the input data as well as the privacy of the trees. However, naively extending private inference over decision trees to private inference over decision forests by replicating the protocols leads to impractical running times. In this paper, we propose an efficient private decision inference protocol using homomorphic encryption. We present several optimizations that identify and then remove (approximate) duplication between the trees in a forest, thereby achieving significant improvements in communication and computation cost over the naive approach. To the best of our knowledge, we present the first private inference protocol for highly scalable gradient boosting decision forests. Our protocol's (SilentWood) inference time is faster than the baseline of parallel running the RCC-PDTE protocol by Mahdavi et al. by up to 42.5x, and faster than Zama's Concrete ML XGBoost by up to 27.8x, and faster than SoK-GGG's two-party garbled circuit protocol by 2.94x.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15494
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SilentWood: Private Inference Over Gradient-Boosting Decision Forests
Ko, Ronny
Kati, Abdelkarim
Geelen, Robin
Mahdavi, Rasoul Akhavan
Yoon, Byoungwoo
Shin, Jongho
Moroz, Igor
Jappinen, Anton
Lin, Zhiqiang
Onizuka, Makoto
Kerschbaum, Florian
Cryptography and Security
Databases
Gradient boosting decision forests, used by XGBoost or AdaBoost, offer higher accuracy and lower training times than decision trees for large datasets. Protocols for private inference over decision trees can be used to preserve the privacy of the input data as well as the privacy of the trees. However, naively extending private inference over decision trees to private inference over decision forests by replicating the protocols leads to impractical running times. In this paper, we propose an efficient private decision inference protocol using homomorphic encryption. We present several optimizations that identify and then remove (approximate) duplication between the trees in a forest, thereby achieving significant improvements in communication and computation cost over the naive approach. To the best of our knowledge, we present the first private inference protocol for highly scalable gradient boosting decision forests. Our protocol's (SilentWood) inference time is faster than the baseline of parallel running the RCC-PDTE protocol by Mahdavi et al. by up to 42.5x, and faster than Zama's Concrete ML XGBoost by up to 27.8x, and faster than SoK-GGG's two-party garbled circuit protocol by 2.94x.
title SilentWood: Private Inference Over Gradient-Boosting Decision Forests
topic Cryptography and Security
Databases
url https://arxiv.org/abs/2411.15494