paper-with-me

홈 › Papers

Privacy and Trust Redefined in Federated Machine Learning

2021-03-29 · Pavlos Papadopoulos, Will Abramson, Adam J. Hall, Nikolaos Pitropakis, William J. Buchanan

A common privacy issue in traditional machine learning is that data needs to be disclosed for the training procedures. In situations with highly sensitive data such as healthcare records, accessing this information is challenging and often prohibited. Luckily, privacy-preserving technologies have been developed to overcome this hurdle by distributing the computation of the training and ensuring the data privacy to their owners. The distribution of the computation to multiple participating entities introduces new privacy complications and risks. In this paper, we present a privacy-preserving decentralised workflow that facilitates trusted federated learning among participants. Our proof-of-concept defines a trust framework instantiated using decentralised identity technologies being developed under Hyperledger projects Aries/Indy/Ursa. Only entities in possession of Verifiable Credentials issued from the appropriate authorities are able to establish secure, authenticated communication channels authorised to participate in a federated learning workflow related to mental health data.

📄 PDF Abstract BibTeX arXiv:2103.15753

Code (1)

OpenMined/PyDentity/tree/master/projects/aries-fl 공식 구현

Tasks

BIG-bench Machine LearningFederated LearningPrivacy Preserving

Similar Papers 제목 키워드 기반

FederatedTrust: A Solution for Trustworthy Federated Learning

2023-02-20 · Pedro Miguel Sánchez Sánchez, Alberto Huertas Celdrán, Ning Xie, Gérôme Bovet 외

The rapid expansion of the Internet of Things (IoT) and Edge Computing has presented challenges for centralized Machine and Deep Learning (ML/DL) methods due to the presence of distributed data silos that hold sensitive …

Edge-computingFairnessFederated LearningPrivacy Preserving

Federated Learning in Practice: Reflections and Projections

2024-10-11 · Katharine Daly, Hubert Eichner, Peter Kairouz, H. Brendan McMahan 외

Federated Learning (FL) is a machine learning technique that enables multiple entities to collaboratively learn a shared model without exchanging their local data. Over the past decade, FL systems have achieved substanti…

Federated Learning

Federated Learning with Blockchain-Enhanced Machine Unlearning: A Trustworthy Approach

2024-05-27 · Xuhan Zuo, Minghao Wang, Tianqing Zhu, Lefeng Zhang 외

With the growing need to comply with privacy regulations and respond to user data deletion requests, integrating machine unlearning into IoT-based federated learning has become imperative. Traditional unlearning methods,…

Federated LearningMachine UnlearningManagement

Shuffled Differentially Private Federated Learning for Time Series Data Analytics

2023-07-30 · Chenxi Huang, Chaoyang Jiang, Zhenghua Chen

Trustworthy federated learning aims to achieve optimal performance while ensuring clients' privacy. Existing privacy-preserving federated learning approaches are mostly tailored for image data, lacking applications for t…

Activity RecognitionFederated LearningHuman Activity RecognitionPrivacy Preserving+1

Robust Federated Training via Collaborative Machine Teaching using Trusted Instances

2019-05-08 · Yufei Han, Xiangliang Zhang

Federated learning performs distributed model training using local data hosted by agents. It shares only model parameter updates for iterative aggregation at the server. Although it is privacy-preserving by design, feder…

Data PoisoningFederated LearningPrivacy Preserving