Secure Collaborative Training and Inference for XGBoost

10/06/2020
by   Andrew Law, et al.
0

In recent years, gradient boosted decision tree learning has proven to be an effective method of training robust models. Moreover, collaborative learning among multiple parties has the potential to greatly benefit all parties involved, but organizations have also encountered obstacles in sharing sensitive data due to business, regulatory, and liability concerns. We propose Secure XGBoost, a privacy-preserving system that enables multiparty training and inference of XGBoost models. Secure XGBoost protects the privacy of each party's data as well as the integrity of the computation with the help of hardware enclaves. Crucially, Secure XGBoost augments the security of the enclaves using novel data-oblivious algorithms that prevent access side-channel attacks on enclaves induced via access pattern leakage.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

02/19/2021

PRICURE: Privacy-Preserving Collaborative Inference in a Multi-Party Setting

When multiple parties that deal with private data aim for a collaborativ...
07/16/2019

Helen: Maliciously Secure Coopetitive Learning for Linear Models

Many organizations wish to collaboratively train machine learning models...
01/09/2020

Secure multiparty computations in floating-point arithmetic

Secure multiparty computations enable the distribution of so-called shar...
10/19/2020

FLAP – A Federated Learning Framework for Attribute-based Access Control Policies

Technology advances in areas such as sensors, IoT, and robotics, enable ...
09/24/2020

Secure Data Sharing With Flow Model

In the classical multi-party computation setting, multiple parties joint...
11/27/2019

SecureGBM: Secure Multi-Party Gradient Boosting

Federated machine learning systems have been widely used to facilitate t...
05/12/2019

Secure Error Correction using Multi-Party Computation

During recent years with the increase of data and data analysis needs, p...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.