Privacy Preserving Machine Learning with Homomorphic Encryption and Federated Learning (2021-04-01T00:00:00.000000Z)

TL;DR

A multi-party privacy preserving machine learning framework, named PFMLP, based on partially homomorphic encryption and federated learning, which is all learning parties just transmitting the encrypted gradients by homomorphicryption.

Abstract

Privacy protection has been an important concern with the great success of machine learning. In this paper, it proposes a multi-party privacy preserving machine learning framework, named PFMLP, based on partially homomorphic encryption and federated learning. The core idea is all learning parties just transmitting the encrypted gradients by homomorphic encryption. From experiments, the model trained by PFMLP has almost the same accuracy, and the deviation is less than 1%. Considering the computational overhead of homomorphic encryption, we use an improved Paillier algorithm which can speed up the training by 25–28%. Moreover, comparisons on encryption key length, the learning network structure, number of learning clients, etc. are also discussed in detail in the paper.

Authors

H. Fang

1 papers

Q. Qian

1 papers

TL;DR

Abstract

Authors

References50 items

More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligence

Fast Decryption Algorithm for Paillier Homomorphic Cryptosystem

HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learning

Fast Cloud–Paillier homomorphic schemes for protecting confidentiality of sensitive data in cloud computing

Federated Learning Of Out-Of-Vocabulary Words

Patient Clustering Improves Efficiency of Federated Machine Learning to predict mortality and hospital stay time using distributed Electronic Medical Records

Towards Federated Learning at Scale: System Design

Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation System

SecureBoost: A Lossless Federated Learning Framework

Secure Federated Transfer Learning

A Hybrid Approach to Privacy-Preserving Federated Learning

APPLIED FEDERATED LEARNING: IMPROVING GOOGLE KEYBOARD QUERY SUGGESTIONS

Federated Learning for Mobile Keyboard Prediction

Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation

Privacy-Preserving Ridge Regression with only Linearly-Homomorphic Encryption

Adaptive Federated Learning in Resource Constrained Edge Computing Systems

CPP-ELM: Cryptographically Privacy-Preserving Extreme Learning Machine for Cloud Systems

Practical Secure Aggregation for Privacy-Preserving Machine Learning

Homomorphic Encryption as a Service for Outsourced Images in Mobile Cloud Computing Environment

Membership Inference Attacks Against Machine Learning Models

Federated Learning: Strategies for Improving Communication Efficiency

Ako: Decentralised Deep Learning with Partial Gradient Exchange

Deep Learning with Differential Privacy

CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy

STRADS: a distributed framework for scheduled model parallel machine learning

Distributed Machine Learning via Sufficient Factor Broadcasting

Privacy-preserving deep learning

Managed communication and consistency for fast data-parallel iterative analytics

The Algorithmic Foundations of Differential Privacy

On parallelizability of stochastic gradient descent for speech DNNS

Petuum: A New Platform for Distributed Machine Learning on Big Data

More Effective Distributed ML via a Stale Synchronous Parallel Parameter Server

Deep learning with COTS HPC systems

Large Scale Distributed Deep Networks

Implementing digital signature with RSA encryption algorithm to enhance the Data Security of cloud in Cloud Computing

Fully Homomorphic Encryption over the Integers

Fully homomorphic encryption using ideal lattices

Public-Key Cryptosystems Based on Composite Degree Residuosity Classes

Fair exchange with a semi-trusted third party (extended abstract)

BatchCrypt: Efficient Homomorphic Encryption for Cross-Silo Federated Learning

A homomorphic-encryption-based vertical federated learning scheme for rick management

Homomorphic Encryption

Encryption Performance Improvements of the Paillier Cryptosystem

Privacy Preserving Back-Propagation Neural Network Learning Made Practical with Cloud Computing

Materials Database

Secure multiple linear regression based on homomorphic encryption

The Rsa Cryptosystem: History, Algorithm, Primes; Fundamental Concepts of Encryption; University of Chicago: Chicago

Gradient-based learning applied to document recognition

Secure Multi-Party Computation; Manuscript. Preliminary Version

ON DATA BANKS AND PRIVACY HOMOMORPHISMS

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL