Federated Learning: Opportunities and Challenges (2021-01-14T00:00:00.000000Z)

TL;DR

While FL appears to be a promising Machine Learning technique to keep the local data private, it is also vulnerable to attacks like other ML models.

Abstract

Federated Learning (FL) is a concept first introduced by Google in 2016, in which multiple devices collaboratively learn a machine learning model without sharing their private data under the supervision of a central server. This offers ample opportunities in critical domains such as healthcare, finance etc, where it is risky to share private user information to other organisations or devices. While FL appears to be a promising Machine Learning (ML) technique to keep the local data private, it is also vulnerable to attacks like other ML models. Given the growing interest in the FL domain, this report discusses the opportunities and challenges in federated learning.

Authors

P. Mammen

1 papers

TL;DR

Abstract

Authors

References39 items

Federated Learning: Collaborative Machine Learning without Centralized Training Data

A survey on security and privacy of federated learning

FLaaS: Federated Learning as a Service

Federated learning for privacy-preserving AI

BlockFLA: Accountable Federated Learning via Hybrid Blockchain Architecture

Distilled One-Shot Federated Learning

Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications

Federated Machine Learning in Vehicular Networks: A summary of Recent Applications

Asynchronous Federated Learning with Reduced Number of Rounds and with Differential Privacy from Less Aggregated Gaussian Noise

Data Poisoning Attacks Against Federated Learning Systems

Blockchain-Federated-Learning and Deep Learning Models for COVID-19 Detection Using CT Imaging

A Sustainable Incentive Scheme for Federated Learning

Data Poisoning Attacks on Federated Machine Learning

Learning Context-Aware Policies from Multiple Smart Homes via Federated Multi-Task Learning

Privacy-Preserving Traffic Flow Prediction: A Federated Learning Approach

A Learning-Based Incentive Mechanism for Federated Learning

Advances and Open Problems in Federated Learning

Local Model Poisoning Attacks to Byzantine-Robust Federated Learning

Can You Really Backdoor Federated Learning?

Federated Learning for Edge Networks: Resource Optimization and Incentive Mechanism

BAFFLE : Blockchain Based Aggregator Free Federated Learning

Federated Learning: Challenges, Methods, and Future Directions

FLChain: A Blockchain for Auditable Federated Learning with Trust and Incentive

CMFL: Mitigating Communication Overhead for Federated Learning

Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach

Asynchronous Federated Optimization

One-Shot Federated Learning

Towards Federated Learning at Scale: System Design

Asynchronous Federated Learning for Geospatial Applications

How To Backdoor Federated Learning

A Review of Challenges and Opportunities in Machine Learning for Health.

Differentially Private Federated Learning: A Client Level Perspective

Mastering the game of Go without human knowledge

Gaia: Geo-Distributed Machine Learning Approaching LAN Speeds

Federated Learning: Strategies for Improving Communication Efficiency

Communication-Efficient Learning of Deep Networks from Decentralized Data

BatchCrypt: Efficient Homomorphic Encryption for Cross-Silo Federated Learning

Decentralizing Large-Scale Natural Language Processing with Federated Learning

Efficient and Private Federated Learning using TEE

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names