Secure & Private Federated Neuroimaging Article Swipe

MAKE IMPACT

Dimitris Stripelis , Umang Gupta , Hamza Saleem , Nikhil J. Dhinagar , Tanmay Ghai , Rafael Sánchez , Chrysovalantis Anastasiou , Armaghan Asghar , Greg Ver Steeg , Srivatsan Ravi , Muhammad Naveed , Paul M. Thompson , José Luis Ambite · YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2205.05249

The amount of biomedical data continues to grow rapidly. However, collecting data from multiple sites for joint analysis remains challenging due to security, privacy, and regulatory concerns. To overcome this challenge, we use Federated Learning, which enables distributed training of neural network models over multiple data sources without sharing data. Each site trains the neural network over its private data for some time, then shares the neural network parameters (i.e., weights, gradients) with a Federation Controller, which in turn aggregates the local models, sends the resulting community model back to each site, and the process repeats. Our Federated Learning architecture, MetisFL, provides strong security and privacy. First, sample data never leaves a site. Second, neural network parameters are encrypted before transmission and the global neural model is computed under fully-homomorphic encryption. Finally, we use information-theoretic methods to limit information leakage from the neural model to prevent a curious site from performing model inversion or membership attacks. We present a thorough evaluation of the performance of secure, private federated learning in neuroimaging tasks, including for predicting Alzheimer's disease and estimating BrainAGE from magnetic resonance imaging (MRI) studies, in challenging, heterogeneous federated environments where sites have different amounts of data and statistical distributions.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2205.05249

PDF

https://arxiv.org/pdf/2205.05249

OA Status

green

Cited By

3

Related Works

10

OpenAlex ID

https://openalex.org/W4280540325

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4280540325

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2205.05249

Digital Object Identifier

Title

Secure & Private Federated Neuroimaging

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2022

Year of publication

Publication date

2022-05-11

Full publication date if available

Authors

Dimitris Stripelis, Umang Gupta, Hamza Saleem, Nikhil J. Dhinagar, Tanmay Ghai, Rafael Sánchez, Chrysovalantis Anastasiou, Armaghan Asghar, Greg Ver Steeg, Srivatsan Ravi, Muhammad Naveed, Paul M. Thompson, José Luis Ambite

List of authors in order

Landing page

https://arxiv.org/abs/2205.05249

Publisher landing page

PDF URL

https://arxiv.org/pdf/2205.05249

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2205.05249

Direct OA link when available

Concepts

Computer science, Homomorphic encryption, Artificial neural network, Encryption, Neuroimaging, Private information retrieval, Information sensitivity, Computer security, Data mining, Artificial intelligence, Machine learning, Computer network, Psychology, Psychiatry

Top concepts (fields/topics) attached by OpenAlex

Cited by

3

Total citation count in OpenAlex

Citations by year (recent)

2024: 2, 2023: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload