mlsanityData to 7 Oct 2026

Secure & Private Federated Neuroimaging

arXiv 2205.05249 ↗First posted 11 May 2022cs.LG cs.CR cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 74 references that are in the map. First posted on arXiv 11 May 2022.

Builds on

31 of 74 references.

References · 31

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016Deep Learning with Differential Privacycited by 2,682
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  5. 2020Adaptive Federated Optimizationcited by 1,036
  6. 2019Deep Leakage from Gradientscited by 1,004
  7. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  8. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  9. 2020The Future of Digital Health with Federated Learningcited by 625
  10. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  11. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  12. 2021A Field Guide to Federated Optimizationcited by 312
19 more
  1. 2017Image reconstruction by domain transform manifold learningcited by 231
  2. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
  3. 2018Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentationcited by 148
  4. 2020Local Differential Privacy based Federated Learning for Internet of Thingscited by 74
  5. 2021Differentially Private Federated Learning on Heterogeneous Datacited by 74
  6. 2016Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarkercited by 72
  7. 2018Federated Learning in Distributed Medical Databases: Meta-Analysis of Large-Scale Subcortical Brain Datacited by 46
  8. 2021Privacy-preserving Federated Learning based on Multi-key Homomorphic Encryptioncited by 46
  9. 2022Do Gradient Inversion Attacks Make Federated Learning Unsafe?cited by 44
  10. 2018Towards Demystifying Membership Inference Attackscited by 39
  11. 2019Unsupervised Deep Learning for Bayesian Brain MRI Segmentationcited by 20
  12. 2021Membership Inference Attacks on Deep Regression Models for Neuroimagingcited by 19
  13. 2021Secure Neuroimaging Analysis using Federated Learning with Homomorphic Encryptioncited by 18
  14. 2021Semi-Synchronous Federated Learning for Energy-Efficient Training and Accelerated Convergence in Cross-Silo Settingscited by 11
  15. 2021Improved Brain Age Estimation with Slice-based Set Networkscited by 11
  16. 2021Scaling Neuroscience Research using Federated Learningcited by 10
  17. 2020Accelerating Federated Learning in Heterogeneous Data and Computational Environmentscited by 6
  18. 2020An Extension of Fano's Inequality for Characterizing Model Susceptibility to Membership Inference Attackscited by 5
  19. 2022Performance Weighting for Robust Federated Learning Against Corrupted Sourcescited by 5

Built on by

Not cited yet.