SoK: Training Machine Learning Models over Multiple Sources with Privacy Preservation

2020-12-06 · Lushan Song, Guopeng Lin, Jiaxuan Wang, Haoqi Wu, Wenqiang Ruan, Weili Han

Nowadays, gathering high-quality training data from multiple data sources with privacy preservation is a crucial challenge to training high-performance machine learning models. The potential solutions could break the barriers among isolated data corpus, and consequently enlarge the range of data available for processing. To this end, both academic researchers and industrial vendors are recently strongly motivated to propose two main-stream folders of solutions mainly based on software constructions: 1) Secure Multi-party Learning (MPL for short); and 2) Federated Learning (FL for short). The above two technical folders have their advantages and limitations when we evaluate them according to the following five criteria: security, efficiency, data distribution, the accuracy of trained models, and application scenarios. Motivated to demonstrate the research progress and discuss the insights on the future directions, we thoroughly investigate these protocols and frameworks of both MPL and FL. At first, we define the problem of Training machine learning Models over Multiple data sources with Privacy Preservation (TMMPP for short). Then, we compare the recent studies of TMMPP from the aspects of the technical routes, the number of parties supported, data partitioning, threat model, and machine learning models supported, to show their advantages and limitations. Next, we investigate and evaluate five popular FL platforms. Finally, we discuss the potential directions to resolve the problem of TMMPP in the future.

📄 PDF Abstract BibTeX arXiv:2012.03386

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning Federated LearningPrivacy Preserving

NN-EMD: Efficiently Training Neural Networks using Encrypted Multi-Sourced Datasets

2020-12-18 · Runhua Xu, James Joshi, Chao Li

Training a machine learning model over an encrypted dataset is an existing promising approach to address the privacy-preserving machine learning task, however, it is extremely challenging to efficiently train a deep neur…

BIG-bench Machine Learning Privacy Preserving

ESCAPED: Efficient Secure and Private Dot Product Framework for Kernel-based Machine Learning Algorithms with Applications in Healthcare

2020-12-04 · Ali Burak Ünal, Mete Akgün, Nico Pfeifer

To train sophisticated machine learning models one usually needs many training samples. Especially in healthcare settings these samples can be very expensive, meaning that one institution alone usually does not have enou…

BIG-bench Machine Learning Clustering Dimensionality Reduction

Private Multi-Task Learning: Formulation and Applications to Federated Learning

2021-08-30 · Shengyuan Hu, Zhiwei Steven Wu, Virginia Smith

Many problems in machine learning rely on multi-task learning (MTL), in which the goal is to solve multiple related machine learning tasks simultaneously. MTL is particularly relevant for privacy-sensitive applications i…

BIG-bench Machine Learning Distributed Optimization Federated Learning Multi-Task Learning+1

PiPar: Pipeline Parallelism for Collaborative Machine Learning

2022-12-01 · Zihan Zhang, Philip Rodgers, Peter Kilpatrick, Ivor Spence 외

Collaborative machine learning (CML) techniques, such as federated learning, have been proposed to train deep learning models across multiple mobile devices and a server. CML techniques are privacy-preserving as a local …

Federated Learning Privacy Preserving

Improving the Classification Effect of Clinical Images of Diseases for Multi-Source Privacy Protection

2024-08-23 · Tian Bowen, Xu Zhengyang, Yin Zhihao, Wang Jingying 외

Privacy data protection in the medical field poses challenges to data sharing, limiting the ability to integrate data across hospitals for training high-precision auxiliary diagnostic models. Traditional centralized trai…

Diagnostic Federated Learning