mlsanityData to 14 Oct 2026

Membership Inference Attacks on Deep Regression Models for Neuroimaging

arXiv 2105.02866 ↗First posted 6 May 2021q-bio.QM cs.CR cs.LGcited by 22

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

Ensuring the privacy of research participants is vital, even more so in healthcare environments. Deep learning approaches to neuroimaging require large datasets, and this often necessitates sharing data between multiple sites, which is antithetical to the privacy objectives. Federated learning is a commonly proposed solution to this problem. It circumvents the need for data sharing by sharing parameters during the training process. However, we demonstrate that allowing access to parameters may leak private information even if data is never directly shared. In particular, we show that it is possible to infer if a sample was used to train the model given only access to the model prediction (black-box) or access to the model itself (white-box) and some leaked samples from the training data distribution. Such attacks are commonly referred to as Membership Inference attacks. We show realistic Membership Inference attacks on deep learning models trained for 3D neuroimaging tasks in a centralized as well as decentralized setup. We demonstrate feasible attacks on brain age prediction models (deep learning models that predict a person's age from their brain MRI scan). We correctly identified whether an MRI scan was used in model training with a 60% to over 80% success rate depending on model complexity and security assumptions.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 25 of its 49 references that are in the map. First posted on arXiv 6 May 2021.

Builds on

25 of 49 references.

References · 25

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2016Deep Learning with Differential Privacycited by 2,728
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  5. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  6. 2019Towards Federated Learning at Scale: System Designcited by 832
  7. 2020The Future of Digital Health with Federated Learningcited by 633
  8. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 498
  9. 2020Label-Only Membership Inference Attackscited by 388
  10. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 292
  11. 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 186
  12. 2019Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inferencecited by 175
13 more
  1. 2019Privacy-preserving Federated Brain Tumour Segmentationcited by 169
  2. 2018Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentationcited by 149
  3. 2020Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Resultscited by 122
  4. 2019BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learningcited by 117
  5. 2020Revisiting Membership Inference Under Realistic Assumptionscited by 112
  6. 2016Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarkercited by 72
  7. 2017Knock Knock, Who's There? Membership Inference on Aggregate Location Datacited by 70
  8. 2018Federated Learning in Distributed Medical Databases: Meta-Analysis of Large-Scale Subcortical Brain Datacited by 46
  9. 2018Towards Demystifying Membership Inference Attackscited by 40
  10. 2021Improved Brain Age Estimation with Slice-based Set Networkscited by 11
  11. 2021Scaling Neuroscience Research using Federated Learningcited by 10
  12. 2020An Extension of Fano's Inequality for Characterizing Model Susceptibility to Membership Inference Attackscited by 5
  13. 2019Interpreting Epsilon of Differential Privacy in Terms of Advantage in Guessing or Approximating Sensitive Attributescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 5; 2023: 4; 2024: 3; 2025: 4; 2026: 3.

22 papers.

Sort:

By area:

  1. 2022Recovering Private Text in Federated Learning of Language Modelscited by 70
  2. 2021Information-theoretic generalization bounds for black-box learning algorithmscited by 49
  3. 2024Membership Inference Attacks and Defenses in Federated Learning: A Surveycited by 31
  4. 2021Secure Neuroimaging Analysis using Federated Learning with Homomorphic Encryptioncited by 18
  5. 2022Multi-Task Distributed Learning using Vision Transformer with Random Patch Permutationcited by 10
  6. 2021Adaptive Differentially Private Empirical Risk Minimizationcited by 5
  7. 2023Fundamental Limits of Membership Inference Attacks on Machine Learning Modelscited by 5
  8. 2022Towards Sparsified Federated Neuroimaging Models via Weight Pruningcited by 4
  9. 2025Generating Synthetic Data with Formal Privacy Guarantees: State of the Art and the Road Aheadcited by 4
  10. 2022Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Surveycited by 3
  11. 2023Privacy Threats in Stable Diffusion Modelscited by 3
  12. 2025Membership Inference Risks in Quantized Models: A Theoretical and Empirical Studycited by 3
10 more
  1. 2025When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive Learningcited by 3
  2. 2024Inference Attacks: A Taxonomy, Survey, and Promising Directionscited by 2
  3. 2024SoK: Security and Privacy Risks of Healthcare AIcited by 2
  4. 2025Membership Inference Attacks with False Discovery Rate Controlcited by 2
  5. 2023Federated Learning over Harmonized Data Siloscited by 1
  6. 2026SoK: Challenges in Tabular Membership Inference Attackscited by 1
  7. 2022Secure & Private Federated Neuroimagingcited by 0
  8. 2023Single-round Self-supervised Distributed Learning using Vision Transformercited by 0
  9. 2026Kinematics-Induced Multimodal 3D Human Pose Estimation with Subject-Level Privacycited by 0
  10. 2026SoK: Rethinking Membership Inference in Tabular Machine Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025An Efficient Gradient-Based Inference Attack for Federated Learning
  2. 2023Source Inference Attacks: Beyond Membership Inference Attacks in Federated Learning
  3. 2022Perfectly Accurate Membership Inference by a Dishonest Central Server in Federated Learning
  4. 2026Evaluating Differential Privacy Against Membership Inference in Federated Learning: Insights from the NIST Genomics Red Team Challenge
  5. 2022FedHarmony: Unlearning Scanner Bias with Distributed Data
  6. 2026Res-MIA: A Training-Free Resolution-Based Membership Inference Attack on Federated Learning Models
  7. 2021Source Inference Attacks in Federated Learning
  8. 2025Securing Genomic Data Against Inference Attacks in Federated Learning Environments